case study on house price prediction

Cookie Policy

We use cookies to operate this website, improve usability, personalize your experience, and improve our marketing. Privacy Policy .

By clicking "Accept" or further use of this website, you agree to allow cookies.

• Data Science
• Data Analytics
• Machine Learning

Predicting Housing Prices with Linear Regression using Python, pandas, and statsmodels

In this post, we'll walk through building linear regression models to predict housing prices resulting from economic activity.

LearnDataSci is reader-supported. When you purchase through links on our site, earned commissions help support our team of writers, researchers, and designers at no extra cost to you.

You should already know:

• Python fundamentals
• Some Pandas experience

Learn both interactively through dataquest.io

This post will walk you through building linear regression models to predict housing prices resulting from economic activity.

Future posts will cover related topics such as exploratory analysis, regression diagnostics, and advanced regression modeling, but I wanted to jump right in so readers could get their hands dirty with data. If you would like to see anything in particular, feel free to leave a comment below.

Let's dive in.

Article Resources

• Notebook and Data: GitHub
• Libraries: numpy, pandas, matplotlib, seaborn, statsmodels

What is Regression?

Linear regression is a model that predicts a relationship of direct proportionality between the dependent variable (plotted on the vertical or Y axis) and the predictor variables (plotted on the X axis) that produces a straight line, like so:

Linear regression will be discussed in greater detail as we move through the modeling process.

Variable Selection

For our dependent variable we'll use housing_price_index (HPI), which measures price changes of residential housing.

For our predictor variables, we use our intuition to select drivers of macro- (or “big picture”) economic activity, such as unemployment, interest rates, and gross domestic product (total productivity). For an explanation of our variables, including assumptions about how they impact housing prices, and all the sources of data used in this post, see here .

Reading in the Data with pandas

Before anything, let's get our imports for this tutorial out of the way.

The first import is just to change how tables appear in the accompanying notebook, the rest will be explained once they're used:

You can grab the data using the pandas read_csv method directly from GitHub. Alternatively, you can download it locally.

Once we have the data, invoke pandas' merge method to join the data together in a single dataframe for analysis. Some data is reported monthly, others are reported quarterly. No worries. We merge the dataframes on a certain column so each row is in its logical place for measurement purposes. In this example, the best column to merge on is the date column. See below.

Let's get a quick look at our variables with pandas' head method. The headers in bold text represent the date and the variables we'll test for our model. Each row represents a different time period.

Usually, the next step after gathering data would be exploratory analysis. Exploratory analysis is the part of the process where we analyze the variables (with plots and descriptive statistics) and figure out the best predictors of our dependent variable.

For the sake of brevity, we'll skip the exploratory analysis. Keep in the back of your mind, though, that it's of utmost importance and that skipping it in the real world would preclude ever getting to the predictive section.

We'll use ordinary least squares (OLS) , a basic yet powerful way to assess our model.

Ordinary Least Squares Assumptions

OLS measures the accuracy of a linear regression model.

OLS is built on assumptions which, if held, indicate the model may be the correct lens through which to interpret our data. If the assumptions don't hold, our model's conclusions lose their validity.

Take extra effort to choose the right model to avoid Auto-esotericism/Rube-Goldberg’s Disease .

Here are the OLS assumptions:

• Linearity : A linear relationship exists between the dependent and predictor variables. If no linear relationship exists, linear regression isn't the correct model to explain our data.
• No multicollinearity : Predictor variables are not collinear, i.e., they aren't highly correlated. If the predictors are highly correlated, try removing one or more of them. Since additional predictors are supplying redundant information, removing them shouldn't drastically reduce the Adj. R-squared (see below).
• Zero conditional mean : The average of the distances (or residuals) between the observations and the trend line is zero. Some will be positive, others negative, but they won't be biased toward a set of values.
• Homoskedasticity : The certainty (or uncertainty) of our dependent variable is equal across all values of a predictor variable; that is, there is no pattern in the residuals. In statistical jargon, the variance is constant.
• No autocorrelation (serial correlation) : Autocorrelation is when a variable is correlated with itself across observations. For example, a stock price might be serially correlated if one day's stock price impacts the next day's stock price.

Let's begin modeling.

Want to learn more?

Simple linear regression.

Simple linear regression uses a single predictor variable to explain a dependent variable. A simple linear regression equation is as follows:

$$y_i = \alpha + \beta x_i + \epsilon_i$$

$y$ = dependent variable

$\beta$ = regression coefficient

$\alpha$ = intercept (expected mean value of housing prices when our independent variable is zero)

$x$ = predictor (or independent) variable used to predict Y

$\epsilon$ = the error term, which accounts for the randomness that our model can't explain.

Using statsmodels' ols function, we construct our model setting housing_price_index as a function of total_unemployed . We assume that an increase in the total number of unemployed people will have downward pressure on housing prices. Maybe we're wrong, but we have to start somewhere!

The code below shows how to set up a simple linear regression model with total_unemployment as our predictor variable.

To explain:

Adj. R-squared indicates that 95% of housing prices can be explained by our predictor variable, total_unemployed .

The regression coefficient (coef) represents the change in the dependent variable resulting from a one unit change in the predictor variable, all other variables being held constant. In our model, a one unit increase in total_unemployed reduces housing_price_index by 8.33. In line with our assumptions, an increase in unemployment appears to reduce housing prices.

The standard error measures the accuracy of total_unemployed 's coefficient by estimating the variation of the coefficient if the same test were run on a different sample of our population. Our standard error, 0.41, is low and therefore appears accurate.

The p-value means the probability of an 8.33 decrease in housing_price_index due to a one unit increase in total_unemployed is 0%, assuming there is no relationship between the two variables. A low p-value indicates that the results are statistically significant, that is in general the p-value is less than 0.05.

The confidence interval is a range within which our coefficient is likely to fall. We can be 95% confident that total_unemployed 's coefficient will be within our confidence interval, [-9.185, -7.480].

Regression Plots

Please see the four graphs below.

• The “Y and Fitted vs. X” graph plots the dependent variable against our predicted values with a confidence interval. The inverse relationship in our graph indicates that housing_price_index and total_unemployed are negatively correlated, i.e., when one variable increases the other decreases.
• The “Residuals versus total_unemployed ” graph shows our model's errors versus the specified predictor variable. Each dot is an observed value; the line represents the mean of those observed values. Since there's no pattern in the distance between the dots and the mean value, the OLS assumption of homoskedasticity holds.
• The “Partial regression plot” shows the relationship between housing_price_index and total_unemployed , taking in to account the impact of adding other independent variables on our existing total_unemployed coefficient. We'll see later how this same graph changes when we add more variables.
• The Component and Component Plus Residual (CCPR) plot is an extension of the partial regression plot, but shows where our trend line would lie after adding the impact of adding our other independent variables on our existing total_unemployed coefficient. More on this plot here .

The next plot graphs our trend line (green), the observations (dots), and our confidence interval (red).

Multiple Linear Regression

Mathematically, multiple linear regression is:

$$Y = \beta_0 + \beta_1 x_1 + \beta_2 x_2 + ... + \beta_k x_k + \epsilon$$

We know that unemployment cannot entirely explain housing prices. To get a clearer picture of what influences housing prices, we add and test different variables and analyze the regression results to see which combinations of predictor variables satisfy OLS assumptions, while remaining intuitively appealing from an economic perspective.

We arrive at a model that contains the following variables: fed_funds , consumer_price_index , long_interest_rate , and gross_domestic_product , in addition to our original predictor, total_unemployed .

Adding the new variables decreased the impact of total_unemployed on housing_price_index . total_unemployed ‘s impact is now more unpredictable ( standard error increased from 0.41 to 2.399), and, since the p-value is higher (from 0 to 0.943), less likely to influence housing prices.

Although total_unemployed may be correlated with housing_price_index , our other predictors seem to capture more of the variation in housing prices. The real-world interconnectivity among our variables can't be encapsulated by a simple linear regression alone; a more robust model is required. This is why our multiple linear regression model's results change drastically when introducing new variables.

That all our newly introduced variables are statistically significant at the 5% threshold, and that our coefficients follow our assumptions, indicates that our multiple linear regression model is better than our simple linear model.

The code below sets up a multiple linear regression with our new predictor variables.

Another Look at Partial Regression Plots

Now let's plot our partial regression graphs again to visualize how the total_unemployed variable was impacted by including the other predictors. The lack of trend in the partial regression plot for total_unemployed (in the figure below, upper right corner), relative to the regression plot for total_unemployed (above, lower left corner), indicates that total unemployment isn't as explanatory as the first model suggested . We also see that the observations from the latest variables are consistently closer to the trend line than the observations for total_unemployment , which reaffirms that fed_funds , consumer_price_index , long_interest_rate , and gross_domestic_product do a better job of explaining housing_price_index .

These partial regression plots reaffirm the superiority of our multiple linear regression model over our simple linear regression model.

We have walked through setting up basic simple linear and multiple linear regression models to predict housing prices resulting from macroeconomic forces and how to assess the quality of a linear regression model on a basic level.

To be sure, explaining housing prices is a difficult problem. There are many more predictor variables that could be used. And causality could run the other way; that is, housing prices could be driving our macroeconomic variables; and even more complex still, these variables could be influencing each other simultaneously.

I encourage you to dig into the data and tweak this model by adding and removing variables while remembering the importance of OLS assumptions and the regression results.

Most importantly, know that the modeling process, being based in science, is as follows: test, analyze, fail, and test some more.

Navigating Pitfalls

This post is an introduction to basic regression modeling, but experienced data scientists will find several flaws in our method and model, including:

• No Lit Review : While it's tempting to dive in to the modeling process, ignoring the existing body of knowledge is perilous. A lit review might have revealed that linear regression isn't the proper model to predict housing prices. It also might have improved variable selection. And spending time on a lit review at the outset can save a lot of time in the long run.
• Small sample size : Modeling something as complex as the housing market requires more than six years of data. Our small sample size is biased toward the events after the housing crisis and is not representative of long-term trends in the housing market.
• Multicollinearity : A careful observer would've noticed the warnings produced by our model regarding multicollinearity. We have two or more variables telling roughly the same story, overstating the value of each of the predictors.
• Autocorrelation : Autocorrelation occurs when past values of a predictor influence its current and future values. Careful reading of the Durbin-Watson score would've revealed that autocorrelation is present in our model.

In a future post, we'll attempt to resolve these flaws to better understand the economic predictors of housing prices.

Course Recommendations

Further learning:, machine learning with python — coursera, get updates in your inbox.

Join over 7,500 data science learners.

Recent articles:

The 9 best ai courses online for 2024: beginner to advanced, the 6 best python courses for 2024 – ranked by software engineer, best course deals for black friday and cyber monday 2024, sigmoid function, 7 best artificial intelligence (ai) courses.

Top courses you can take today to begin your journey into the Artificial Intelligence field.

Meet the Authors

A graduate of Belmont University, Tim is a Nashville, TN-based software engineer and statistician at Perception Health, an industry leader in healthcare analytics, and co-founder of Sidekick, LLC, a data consulting company. Find him on  Twitter  and  GitHub .

John is a research analyst at Laffer Associates, a macroeconomic consulting firm based in Nashville, TN. He graduated from Belmont University. Find him on  GitHub  and  LinkedIn

Back to blog index

• Real Estate Economics

House Price Prediction using a Machine Learning Model: A Survey of Literature

• December 2020
• International Journal of Modern Education and Computer Science 12(6):46-54
• 12(6):46-54
• This person is not on ResearchGate, or hasn't claimed this research yet.

• Universiti Teknologi MARA

• Universiti Pendidikan Sultan Idris (UPSI)

Discover the world's research

• 25+ million members
• 160+ million publication pages
• 2.3+ billion citations

• Mardhiati Sulaimi

• Qiuhui Feng
• Zhenhua Lei

• Pancham Singh
• Ujjwal Agarwal
• Manish Dixit

• Arman Sankibayev
• Rozamgul Niyazova
• Gulnara Akimbekova

• Suhas Shastry H.S
• Soumyadeep Roy
• Shiza Mehek S.K
• Dr. Ananthapadmanabha T
• Satyam Kumar Deepu
• Abhinav Verma
• Kriti Bharat
• Prof. Dipali Mane
• K. Sudheer Reddy

• T. Ashalatha
• B. Ravi Raju

• Melek Akgün

• Reza Akhavian

• E.Obiri-Yeboah

• MAURICIO RODRIGUEZ
• Int J Hous Market Anal

• Wei Cheng Choong

• Pragati Jaiswal

• A. Ambikapathy
• HABITAT INT

• The Danh Phan

• Abhijit Sarma

• Rohini Nair
• Recruit researchers
• Join for free
• Login Email Tip: Most researchers use their institutional email address as their ResearchGate login Password Forgot password? Keep me logged in Log in or Continue with Google Welcome back! Please log in. Email · Hint Tip: Most researchers use their institutional email address as their ResearchGate login Password Forgot password? Keep me logged in Log in or Continue with Google No account? Sign up

A Comparative Study of Machine Learning Models for House Price Prediction and Analysis in Smart Cities

• Conference paper
• First Online: 16 September 2023
• Cite this conference paper

• Mrignainy Kansal 9 ,
• Pancham Singh 9 ,
• Shambhavi Shukla 10 &
• Sakshi Srivastava 10  

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1888))

Included in the following conference series:

• International Conference on Electronic Governance with Emerging Technologies

230 Accesses

5 Citations

Developing any precise or exact prediction of house prices is an unsettled task for many years. It is the social as well as economic need for the welfare & comfort of the citizens. During the Covid-19 outbreak policy reforms were introduced and various businesses scaled down their workforce so prospective buyers needed to wait for the decision about the purchase of Properties. Thus it became important to provide accurate and accessible solutions to the buyers to mould their decision. The objective and aim of our research work are to provide digital-based solutions to real estate prices because of the increasing growth in online platforms that provide virtual tours. We performed a detailed study to understand the pertinent attributes and the most efficient model built to perform forecasting of the expected price. The results of this analysis verified the use of models like Linear Regression, Random forest Regression, XG Boost, and Voting Regressor as some efficient models. The model that performed fairly well as compared to other models is Random Forest with an accuracy of (98.207) while others with an accuracy of (73.12) for Linear Regression, an accuracy of (95.41) for XG Boost, the accuracy of (94.44) for Voting Regression. Our Findings in this research have advocated the idea that prices of any real estate property are governed by 2 major factors: Its Locality and Construction Composition.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save.

• Get 10 units per month
• Download Article/Chapter or eBook
• 1 Unit = 1 Article or 1 Chapter
• Cancel anytime
• Available as PDF
• Read on any device
• Instant download
• Own it forever
• Available as EPUB and PDF
• Compact, lightweight edition
• Dispatched in 3 to 5 business days
• Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Jia, J., Zhang, X., Huang, C., Luan, H.: Multiscale analysis of human social sensing of urban appearance and its effects on house price appreciation in Wuhan China. Sustain. Cities Soc. 81 , 103844 (2022)

Article   Google Scholar  

Akar, A.U., Yalpir, S.: Using svr and mra methods for real estate valuation in the smart cities. Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci. 46 , 21–26 (2021)

Arcuri, N., De Ruggiero, M., Salvo, F., Zinno, R.: Automated valuation methods through the cost approach in a BIM and GIS integration framework for smart city appraisals. Sustainability. 12 , 7546 (2020)

Varma, A., Sarma, A., Doshi, S., Nair, R.: House price prediction using machine learning and neural networks. In: 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), pp. 1936–1939. IEEE (2018)

Google Scholar  

Thamarai, M., Malarvizhi, S.P.: House price prediction modeling using machine learning. Int. J. Inf. Eng. Electron. Bus. 12 , 15 (2020)

Truong, Q., Nguyen, M., Dang, H., Mei, B.: Housing price prediction via improved machine learning techniques. Procedia Comput. Sci. 174 , 433–442 (2020)

Wang, P.-Y., Chen, C.-T., Su, J.-W., Wang, T.-Y., Huang, S.-H.: Deep learning model for house price prediction using heterogeneous data analysis along with joint self-attention mechanism. IEEE Access 9 , 55244–55259 (2021)

Adetunji, A.B., Akande, O.N., Ajala, F.A., Oyewo, O., Akande, Y.F., Oluwadara, G.: House price prediction using random forest machine learning technique. Procedia Comput. Sci. 199 , 806–813 (2022)

Karimi, Y., Haghi Kashani, M., Akbari, M., Mahdipour, E.: Leveraging big data in smart cities: a systematic review. Concurrency Comput. Pract. Exp. 33 , e6379 (2021)

Bilen, T., Erel-Özçevik, M., Yaslan, Y., Oktug, S.F.: A smart city application: business location estimator using machine learning techniques. In: 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pp. 1314–1321. IEEE (2018)

Zhang, C., Zuo, J., Wu, Y., Zhang, J., Liu, J., Chang, X.: Application of combined neural network based on entropy method in smart city forecast problem. In: 2020 International Conference on Artificial Intelligence and Computer Engineering (ICAICE), pp. 378–382. IEEE (2020)

Ja’afar, N.S., Mohamad, J., Ismail, S.: Machine learning for property price prediction and price valuation: a systematic literature review. Plan. Malaysia 19 , 1018 (2021)

Shahhosseini, M., Hu, G., Pham, H.: Optimizing ensemble weights for machine learning models: a case study for housing price prediction. In: Yang, H., Qiu, R., Chen, W. (eds.) Smart Service Systems, Operations Management, and Analytics. INFORMS-CSS 2019. Springer Proceedings in Business and Economics, pp. 87–97. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-30967-1_9

Kumar, G.K., Rani, D.M., Koppula, N., Ashraf, S.: Prediction of house price using machine learning algorithms. In: 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI), pp. 1268–1271. IEEE (2021)

Bagheri, B., Shaykh-Baygloo, R.: Spatial analysis of urban smart growth and its effects on housing price: The case of Isfahan. Iran. Sustain. Cities Soc. 68 , 102769 (2021)

Cooke, P.: Silicon Valley imperialists create new model villages as smart cities in their own image. J. Open Innov. Technol. Market Complex. 6 , 24 (2020)

Rawool, A.G., Rogye, D.V., Rane, S.G., Bharadi, V.A.: House price prediction using machine learning. Int. J. Res. Appl. Sci. Eng. Technol. 9 , 686–692 (2021)

Yu, L., Jiao, C., Xin, H., Wang, Y., Wang, K.: Prediction on housing price based on deep learning. Int. J. Comput. Inf. Eng. 12 , 90–99 (2018)

Kang, Y., et al.: Understanding house price appreciation using multi-source big geo-data and machine learning. Land Use Policy 111 , 104919 (2021)

Shamsuddin, S., Srinivasan, S.: Just smart or just and smart cities? Assessing the literature on housing and information and communication technology. Hous. Policy Debate 31 , 127–150 (2021)

Kisia\la, W., Rącka, I.: Spatial and statistical analysis of urban poverty for sustainable city development. Sustainability 13 , 858 (2021)

Afonso, B., Melo, L., Oliveira, W., Sousa, S., Berton, L.: Housing prices prediction with a deep learning and random forest ensemble. In: Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional. pp. 389–400. SBC (2019)

Ahtesham, M., Bawany, N.Z., Fatima, K.: House price prediction using machine learning algorithm-the case of Karachi city, Pakistan. In: 2020 21st International Arab Conference on Information Technology (ACIT), pp. 1–5. IEEE (2020)

Muhammad, A.N., Aseere, A.M., Chiroma, H., Shah, H., Gital, A.Y., Hashem, I.A.T.: Deep learning application in smart cities: recent development, taxonomy, challenges and research prospects. Neural Comput. Appl. 33 , 2973–3009 (2021)

Pai, P.-F., Wang, W.-C.: Using machine learning models and actual transaction data for predicting real estate prices. Appl. Sci. 10 , 5832 (2020)

Yazdani, M.: Machine learning, deep learning, and hedonic methods for real estate price prediction. arXiv preprint arXiv:2110.07151 . (2021)

Lu, S., Li, Z., Qin, Z., Yang, X., Goh, R.S.M.: A hybrid regression technique for house prices prediction. In: 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), pp. 319–323. IEEE (2017)

Jain, M., Rajput, H., Garg, N., Chawla, P.: Prediction of house pricing using machine learning with Python. In: 2020 International Conference on Electronics and Sustainable Communication Systems (ICESC), pp. 570–574. IEEE (2020)

Mohd, T., Jamil, N.S., Johari, N., Abdullah, L., Masrom, S.: An overview of real estate modelling techniques for house price prediction. In: Kaur, N., Ahmad, M. (eds.) Charting a Sustainable Future of ASEAN in Business and Social Sciences, vol. 1. pp. 321–338. Springer, Singapore (2020). https://doi.org/10.1007/978-981-15-3859-9_28

Mora-Garcia, R.-T., Cespedes-Lopez, M.-F., Perez-Sanchez, V.R.: housing price prediction using machine learning algorithms in COVID-19 times. Land. 11 , 2100 (2022). https://doi.org/10.3390/land11112100

Download references

Author information

Authors and affiliations.

Department of Information Technology, Ajay Kumar Garg Engineering College, Ghaziabad, Uttar Pradesh, India

Mrignainy Kansal & Pancham Singh

Department of Computer Science and Information Technology, Ajay Kumar Garg Engineering College, Ghaziabad, Uttar Pradesh, India

Shambhavi Shukla & Sakshi Srivastava

You can also search for this author in PubMed   Google Scholar

Corresponding author

Correspondence to Mrignainy Kansal .

Editor information

Editors and affiliations.

Tamaulipas Autonomous University, Reynosa, Tamaulipas, Mexico

Fernando Ortiz-Rodríguez

Autonomous University of Tamaulipas, Reynosa, Tamaulipas, Mexico

Sanju Tiwari

University of Uyo, Uyo, Nigeria

Patience Usoro Usip

Poznan Supercomputing and Networking Center, Poznan, Poland

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Cite this paper.

Kansal, M., Singh, P., Shukla, S., Srivastava, S. (2023). A Comparative Study of Machine Learning Models for House Price Prediction and Analysis in Smart Cities. In: Ortiz-Rodríguez, F., Tiwari, S., Usoro Usip, P., Palma, R. (eds) Electronic Governance with Emerging Technologies. EGETC 2023. Communications in Computer and Information Science, vol 1888. Springer, Cham. https://doi.org/10.1007/978-3-031-43940-7_14

Download citation

DOI : https://doi.org/10.1007/978-3-031-43940-7_14

Published : 16 September 2023

Publisher Name : Springer, Cham

Print ISBN : 978-3-031-43939-1

Online ISBN : 978-3-031-43940-7

eBook Packages : Computer Science Computer Science (R0)

Share this paper

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Publish with us

Policies and ethics

• Find a journal
• Track your research

Information

• Author Services

Initiatives

You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .

Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.

Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.

Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.

Original Submission Date Received: .

• Active Journals
• Find a Journal
• Proceedings Series
• For Authors
• For Reviewers
• For Editors
• For Librarians
• For Publishers
• For Societies
• For Conference Organizers
• Open Access Policy
• Institutional Open Access Program
• Special Issues Guidelines
• Editorial Process
• Research and Publication Ethics
• Article Processing Charges
• Testimonials
• Preprints.org
• SciProfiles
• Encyclopedia

Article Menu

• Subscribe SciFeed
• Recommended Articles
• Google Scholar
• on Google Scholar
• Table of Contents

Find support for a specific problem in the support section of our website.

Please let us know what you think of our products and services.

Visit our dedicated information section to learn more about MDPI.

JSmol Viewer

Housing price prediction using machine learning algorithms in covid-19 times.

1. Introduction

1.1. house prices and machine learning, 1.2. house prices and covid-19, 2. materials and methods, 2.1. study area, information sources, and database, 2.2. descriptive statistics, 2.3. methodology, 3.1. model training and optimization, 3.2. model evaluation and selection.

• The difference in performance between the algorithms (in this case being minimal, varying between 0.9135 and 0.9192 (R² score));
• The need to select an algorithm that has no overfitting problems and generalizes well with unseen data (in this case, the xgbm and lgbm algorithms may be good candidates);
• The need to choose an algorithm with low prediction variability in the cross-validation process (low variance) (the gbr algorithm has had the lowest variability);
• The need to consider the necessary times for the training and optimization of the hyperparameters and whether they adapt to the project deadlines (in this case, the xgbm and lgbm algorithms are the best options);
• The need to consider the file sizes of the models required for deployment (in this case, the lgbm algorithm generates the smallest file and the rf and et algorithms generate the largest (77 to 112 times larger than the lgbm algorithm)).

3.3. Model Interpretation

4. discussion, 5. conclusions, author contributions, institutional review board statement, informed consent statement, data availability statement, acknowledgments, conflicts of interest, abbreviations.

• Kauko, T.; d’Amato, M. Introduction: Suitability Issues in Mass Appraisal Methodology. In Mass Appraisal Methods ; Blackwell Publishing Ltd.: Oxford, UK, 2008; pp. 1–24. [ Google Scholar ] [ CrossRef ]
• Grover, R. Mass valuations. J. Prop. Investig. Financ. 2016 , 34 , 191–204. [ Google Scholar ] [ CrossRef ]
• IAAO, International Association of Assessing Officers. Standard on Mass Appraisal of Real Property (2017) ; International Association of Assessing Officers: Kansas City, MI, USA, 2019; p. 22. Available online: https://www.iaao.org/media/standards/StandardOnMassAppraisal.pdf (accessed on 22 August 2022).
• Wang, D.; Li, V.J. Mass Appraisal Models of Real Estate in the 21st Century: A Systematic Literature Review. Sustainability 2019 , 11 , 7006. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Antipov, E.A.; Pokryshevskaya, E.B. Mass appraisal of residential apartments: An application of Random forest for valuation and a CART-based approach for model diagnostics. Expert Syst. Appl. 2012 , 39 , 1772–1778. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Park, B.; Bae, J.K. Using machine learning algorithms for housing price prediction: The case of Fairfax County, Virginia housing data. Expert Syst. Appl. 2015 , 42 , 2928–2934. [ Google Scholar ] [ CrossRef ]
• Ahmed Neloy, A.; Sadman Haque, H.M.; Ul Islam, M. Ensemble Learning Based Rental Apartment Price Prediction Model by Categorical Features Factoring. In Proceedings of the 2019 11th International Conference on Machine Learning and Computing, Zhuhai, China, 22–24 February 2019; pp. 350–356. [ Google Scholar ] [ CrossRef ]
• Čeh, M.; Kilibarda, M.; Lisec, A.; Bajat, B. Estimating the Performance of Random Forest versus Multiple Regression for Predicting Prices of the Apartments. ISPRS Int. J. Geo-Inf. 2018 , 7 , 168. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Embaye, W.T.; Zereyesus, Y.A.; Chen, B. Predicting the rental value of houses in household surveys in Tanzania, Uganda and Malawi: Evaluations of hedonic pricing and machine learning approaches. PLoS ONE 2021 , 16 , e0244953. [ Google Scholar ] [ CrossRef ]
• Gnat, S. Property Mass Valuation on Small Markets. Land 2021 , 10 , 388. [ Google Scholar ] [ CrossRef ]
• Hong, J. An Application of XGBoost, LightGBM, CatBoost Algorithms on House Price Appraisal System. Hous. Financ. Res. 2020 , 4 , 33–64. [ Google Scholar ] [ CrossRef ]
• Hong, J.; Choi, H.; Kim, W.-S. A house price valuation based on the random forest approach: The mass appraisal of residential property in South Korea. Int. J. Strateg. Prop. Manag. 2020 , 24 , 140–152. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Jui, J.J.; Imran Molla, M.M.; Bari, B.S.; Rashid, M.; Hasan, M.J. Flat Price Prediction Using Linear and Random Forest Regression Based on Machine Learning Techniques. In Embracing Industry 4.0. Selected Articles from MUCET 2019 ; Mohd Razman, M.A., Mat Yahya, N., Zainal Abidin, A.F., Mat Jizat, J.A., Myung, H., Abdul Karim, M.S., Eds.; Springer: Singapore, 2020; Volume 678, pp. 205–217. [ Google Scholar ] [ CrossRef ]
• Kok, N.; Koponen, E.-L.; Martínez-Barbosa, C.A. Big Data in Real Estate? From Manual Appraisal to Automated Valuation. J. Portf. Manag. 2017 , 43 , 202–211. [ Google Scholar ] [ CrossRef ]
• Rico-Juan, J.R.; Taltavull de La Paz, P. Machine learning with explainability or spatial hedonics tools? An analysis of the asking prices in the housing market in Alicante, Spain. Expert Syst. Appl. 2021 , 171 , 114590. [ Google Scholar ] [ CrossRef ]
• Voutas Chatzidis, I. Prediction of Housing Prices based on Spatial & Social Parameters using Regression & Deep Learning Methods. Master’s Thesis, University of Thessaloniki, Thessaloniki, Greece, 2019. [ Google Scholar ] [ CrossRef ]
• Xu, L.; Li, Z. A New Appraisal Model of Second-Hand Housing Prices in China’s First-Tier Cities Based on Machine Learning Algorithms. Comput. Econ. 2021 , 57 , 617–637. [ Google Scholar ] [ CrossRef ]
• Yilmazer, S.; Kocaman, S. A mass appraisal assessment study using machine learning based on multiple regression and random forest. Land Use Policy 2020 , 99 , 104889. [ Google Scholar ] [ CrossRef ]
• Alfaro-Navarro, J.-L.; Cano, E.L.; Alfaro-Cortés, E.; García, N.; Gámez, M.; Larraz, B. A Fully Automated Adjustment of Ensemble Methods in Machine Learning for Modeling Complex Real Estate Systems. Complexity 2020 , 2020 , 5287263. [ Google Scholar ] [ CrossRef ]
• Canaz Sevgen, S.; Aliefendioğlu, Y. Mass Apprasial With A Machine Learning Algorithm: Random Forest Regression. Bilişim Teknol. Derg. 2020 , 13 , 301–311. [ Google Scholar ] [ CrossRef ]
• De Aquino Afonso, B.K.; Carvalho Melo, L.; Dihanster, W.; Sousa, S.; Berton, L. Housing Prices Prediction with a Deep Learning and Random Forest Ensemble. In Proceedings of the Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2019), Salvador de Bahia, Brazil, 15–18 October 2019; pp. 389–400. [ Google Scholar ] [ CrossRef ]
• Ho, W.K.O.; Tang, B.-S.; Wong, S.W. Predicting property prices with machine learning algorithms. J. Prop. Res. 2021 , 38 , 48–70. [ Google Scholar ] [ CrossRef ]
• Hu, L.; He, S.; Han, Z.; Xiao, H.; Su, S.; Weng, M.; Cai, Z. Monitoring housing rental prices based on social media: An integrated approach of machine-learning algorithms and hedonic modeling to inform equitable housing policies. Land Use Policy 2019 , 82 , 657–673. [ Google Scholar ] [ CrossRef ]
• Pai, P.-F.; Wang, W.-C. Using Machine Learning Models and Actual Transaction Data for Predicting Real Estate Prices. Appl. Sci. 2020 , 10 , 5832. [ Google Scholar ] [ CrossRef ]
• Renigier-Biłozor, M.; Źróbek, S.; Walacik, M.; Janowski, A. Hybridization of valuation procedures as a medicine supporting the real estate market and sustainable land use development during the covid-19 pandemic and afterwards. Land Use Policy 2020 , 99 , 105070. [ Google Scholar ] [ CrossRef ]
• Banerjee, D.; Dutta, S. Predicting the housing price direction using machine learning techniques. In Proceedings of the 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), Chennai, India, 21–22 September 2017; pp. 2998–3000. [ Google Scholar ] [ CrossRef ]
• Fan, C.; Cui, Z.; Zhong, X. House Prices Prediction with Machine Learning Algorithms. In Proceedings of the 2018 10th International Conference on Machine Learning and Computing, Macau, China, 26–28 February 2018; pp. 6–10. [ Google Scholar ] [ CrossRef ]
• Iyer, S.R.; Simkins, B.J. COVID-19 and the Economy: Summary of research and future directions. Financ. Res. Lett. 2022 , 47 , 102801. [ Google Scholar ] [ CrossRef ]
• Mohammed, J.K.; Aliyu, A.A.; Dzukogi, U.A.; Olawale, A.A. The Impact of COVID-19 on Housing Market: A Review of Emerging Literature. Int. J. Real Estate Stud. 2022 , 15 , 66–74. [ Google Scholar ] [ CrossRef ]
• Li, X.; Zhang, C. Did the COVID-19 Pandemic Crisis Affect Housing Prices Evenly in the U.S.? Sustainability 2021 , 13 , 12277. [ Google Scholar ] [ CrossRef ]
• Ouazad, A. Resilient Urban Housing Markets: Shocks Versus Fundamentals. In COVID-19: Systemic Risk and Resilience ; Linkov, I., Keenan, J.M., Trump, B.D., Eds.; Springer International Publishing: Cham, Switzerland, 2021; pp. 299–331. [ Google Scholar ] [ CrossRef ]
• Duca, J.V.; Hoesli, M.; Montezuma, J. The resilience and realignment of house prices in the era of Covid-19. J. Eur. Real Estate Res. 2021 , 14 , 421–431. [ Google Scholar ] [ CrossRef ]
• Battistini, N.; Falagiarda, M.; Gareis, J.; Hackmann, A.; Roma, M. The euro area housing market during the COVID-19 pandemic. Eur. Cent. Banc Econ. Bull. 2021 , 2021 , 115–132. Available online: https://www.ecb.europa.eu/pub/pdf/ecbu/eb202107.en.pdf (accessed on 17 August 2022).
• Alves Álvarez, P.A.; San Juan del Peso, L. The Impact of the COVID-19 Health Crisis on the Housing Market in Spain. Boletín Económico Del Banco De España 2021 , 2021 , 1–15. Available online: https://repositorio.bde.es/handle/123456789/16551 (accessed on 17 August 2022).
• Trojanek, R.; Gluszak, M.; Hebdzynski, M.; Tanas, J. The COVID-19 Pandemic, Airbnb and Housing Market Dynamics in Warsaw. Crit. Hous. Anal. 2021 , 8 , 72–84. [ Google Scholar ] [ CrossRef ]
• Cheung, K.S.; Yiu, C.Y.; Xiong, C. Housing Market in the Time of Pandemic: A Price Gradient Analysis from the COVID-19 Epicentre in China. J. Risk Financ. Manag. 2021 , 14 , 108. [ Google Scholar ] [ CrossRef ]
• Qian, X.; Qiu, S.; Zhang, G. The impact of COVID-19 on housing price: Evidence from China. Financ. Res. Lett. 2021 , 43 , 101944. [ Google Scholar ] [ CrossRef ]
• Tian, C.; Peng, X.; Zhang, X. COVID-19 Pandemic, Urban Resilience and Real Estate Prices: The Experience of Cities in the Yangtze River Delta in China. Land 2021 , 10 , 960. [ Google Scholar ] [ CrossRef ]
• Hu, M.R.; Lee, A.D.; Zou, D. COVID-19 and Housing Prices: Australian Evidence with Daily Hedonic Returns. Financ. Res. Lett. 2021 , 43 , 101960. [ Google Scholar ] [ CrossRef ]
• Kartal, M.T.; Kılıç Depren, S.; Depren, Ö. Housing prices in emerging countries during COVID-19: Evidence from Turkey. Int. J. Hous. Mark. Anal. 2021 . ahead-of-print . [ Google Scholar ] [ CrossRef ]
• Kaynak, S.; Ekinci, A.; Kaya, H.F. The effect of COVID-19 pandemic on residential real estate prices: Turkish case. Quant. Financ. Econ. 2021 , 5 , 623–639. [ Google Scholar ] [ CrossRef ]
• INE, Instituto Nacional de Estadística. Padrón de Población por Municipios. Cifras Oficiales de Población de los Municipios Españoles: Revisión del Padrón Municipal. Available online: https://www.ine.es/dyngs/INEbase/categoria.htm?c=Estadistica_P&cid=1254734710990 (accessed on 10 April 2021).
• MITMA, Ministerio de Transportes, Movilidad y Agenda Urbana. Transacciones Inmobiliarias (Compraventa). Available online: https://www.fomento.gob.es/be2/?nivel=2&orden=34000000 (accessed on 5 July 2022).
• ISCIII, Instituto de Salud Carlos III. COVID-19—Documentación y Datos (cnecovid.isciii.es). Available online: https://cnecovid.isciii.es/covid19/#documentaci%C3%B3n-y-datos (accessed on 5 July 2022).
• Malpezzi, S. Hedonic Pricing Models: A Selective and Applied Review. In Housing Economics and Public Policy ; O’Sullivan, T., Gibb, K., Eds.; Blackwell Science: Great Britain, UK, 2003; pp. 67–89. [ Google Scholar ] [ CrossRef ]
• Horowitz, J.L. The role of the list price in housing markets: Theory and an econometric model. J. Appl. Econom. 1992 , 7 , 115–129. [ Google Scholar ] [ CrossRef ]
• Knight, J.; Sirmans, C.F.; Turnbull, G. List Price Information in Residential Appraisal and Underwriting. J. Real Estate Res. 1998 , 15 , 59–76. [ Google Scholar ] [ CrossRef ]
• Shimizu, C.; Nishimura, K.G.; Watanabe, T. House prices from magazines, realtors, and the land registry. BIS Pap. 2012 , 64 , 29–38. Available online: https://www.bis.org/author/chihiro_shimizu.htm (accessed on 11 October 2022).
• INE, Instituto Nacional de Estadística. Cartografía digitalizada de Secciones Censales. Available online: https://www.ine.es/ss/Satellite?L=es_ES&c=Page&cid=1259952026632&p=1259952026632&pagename=ProductosYServicios%2FPYSLayout (accessed on 10 April 2021).
• INE, Instituto Nacional de Estadística. Estadística Experimental. Atlas de Distribución de Renta de los Hogares. Available online: https://www.ine.es/experimental/atlas/exp_atlas_tab.htm (accessed on 5 July 2021).
• SEC, Sede Electrónica del Catastro Inmobiliario. Información Alfanumérica y Cartografía Vectorial. Available online: https://www.sedecatastro.gob.es/ (accessed on 10 April 2021).
• Mora-Garcia, R.T. Modelo explicativo de las Variables Intervinientes en la Calidad del Entorno Construido de las Ciudades. Ph.D. Thesis, Universidad de Alicante, Alicante, Spain, 2016. Available online: http://hdl.handle.net/10045/65829 (accessed on 8 April 2020).
• IGN, Instituto Geográfico Nacional. Centro Nacional de Información Geográfica (CNIG), Centro de descargas. Available online: https://centrodedescargas.cnig.es/ (accessed on 5 July 2022).
• CECD, Conselleria de Educación, Cultura y Deporte. Centros Docentes de la Comunidad Valenciana. Available online: https://ceice.gva.es/es/web/centros-docentes/descarga-base-de-datos (accessed on 10 April 2020).
• ICV, Institut Cartogràfic Valencià. IDEV, Infraestructura de Datos Espaciales Valenciana. Available online: https://idev.gva.es/ (accessed on 10 April 2020).
• Mora-Garcia, R.T.; Marti-Ciriquian, P.; Perez-Sanchez, R.; Cespedes-Lopez, M.F. A comparative analysis of manhattan, euclidean and network distances. Why are network distances more useful to urban professionals? In Proceedings of the 18th International Multidisciplinary Scientific Geoconference SGEM 2018, Albena, Bulgaria, 30 June–9 July 2018; pp. 3–10. [ Google Scholar ] [ CrossRef ]
• USGS, U.S. Geological Survey. EarthExplorer. Available online: https://earthexplorer.usgs.gov (accessed on 5 July 2020).
• Perez-Sanchez, R.; Mora-Garcia, R.T.; Perez-Sanchez, J.C.; Cespedes-Lopez, M.F. The influence of the characteristics of second-hand properties on their asking prices: Evidence in the Alicante market. Informes de la Construcción 2020 , 72 , e345. [ Google Scholar ] [ CrossRef ]
• Mora-Garcia, R.T.; Cespedes-Lopez, M.F.; Perez-Sanchez, R.; Marti-Ciriquian, P.; Perez-Sanchez, J.C. Determinants of the Price of Housing in the Province of Alicante (Spain): Analysis Using Quantile Regression. Sustainability 2019 , 11 , 437. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Cespedes-Lopez, M.F.; Mora-Garcia, R.T.; Perez-Sanchez, R.; Marti-Ciriquian, P. The Influence of Energy Certification on Housing Sales Prices in the Province of Alicante (Spain). Appl. Sci. 2020 , 10 , 7129. [ Google Scholar ] [ CrossRef ]
• Cespedes-Lopez, M.F.; Perez-Sanchez, R.; Mora-Garcia, R.T. The influence of housing location on energy ratings price premium in Alicante, Spain. Ecol. Econ. 2022 , 201 , 107579. [ Google Scholar ] [ CrossRef ]
• Kain, J.F.; Quigley, J.M. Housing Markets and Racial Discrimination: A Microeconomic Analysis ; National Bureau of Economic Research: New York, NY, USA, 1975; p. 393. Available online: https://EconPapers.repec.org/RePEc:nbr:nberbk:kain75-1 (accessed on 16 March 2022).
• Sirmans, G.S.; Macpherson, D.A.; Zietz, E.N. The composition of hedonic pricing models. J. Real Estate Lit. 2005 , 13 , 3–43. Available online: http://www.jstor.org/stable/44103506 (accessed on 16 March 2022). [ CrossRef ]
• Kleinbaum, D.; Kupper, L.; Nizam, A.; Rosenberg, E. Applied Regression Analysis and Other Multivariable Methods , 5th ed.; Cengage Learning: Boston, MA, USA, 2013; p. 1072. [ Google Scholar ]
• Chatterjee, S.; Simonoff, J.S. Handbook of Regression Analysis ; John Wiley & Sons Inc.: Hoboken, NJ, USA, 2013; p. 240. [ Google Scholar ]
• James, G.; Witten, D.; Hastie, T.; Tibshirani, R. An Introduction to Statistical Learning: With Applications in R , 2nd ed.; Springer: New York, NY, USA, 2021. [ Google Scholar ] [ CrossRef ]
• Linardatos, P.; Papastefanopoulos, V.; Kotsiantis, S. Explainable AI: A Review of Machine Learning Interpretability Methods. Entropy 2021 , 23 , 18. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Korobov, M. Explaining behavior of Machine Learning models with eli5 library. In Proceedings of the EuroPython Congress 2017, Rimini, Italy, 9–16 July 2017. [ Google Scholar ] [ CrossRef ]
• Korobov, M.; Lopuhin, K. ELI5 Python Package. Available online: https://eli5.readthedocs.io/ (accessed on 15 September 2021).
• Johnson, J.W.; Lebreton, J.M. History and Use of Relative Importance Indices in Organizational Research. Organ. Res. Methods 2004 , 7 , 238–257. [ Google Scholar ] [ CrossRef ]
• Grömping, U. Relative Importance for Linear Regression in R: The package relaimpo. J. Stat. Softw. 2006 , 17 , 27. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Friedman, J.H. Greedy Function Approximation: A Gradient Boosting Machine. Ann. Stat. 2001 , 29 , 1189–1232. [ Google Scholar ] [ CrossRef ]
• Molnar, C. (Ed.) Interpretable Machine Learning. A Guide for Making Black Box Models Explainable ; Christoph Molnar Online. , 2021. Available online: https://christophm.github.io/interpretable-ml-book/ (accessed on 15 September 2021).
• McGreal, W.S.; Taltavull de la Paz, P. Implicit house prices: Variation over time and space in Spain. Urban Stud. 2013 , 50 , 2024–2043. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Allen-Coghlan, M.; McQuinn, K.M. The potential impact of Covid-19 on the Irish housing sector. Int. J. Hous. Mark. Anal. 2021 , 14 , 636–651. [ Google Scholar ] [ CrossRef ]
• Aassve, A.; Arpino, B.; Billari, F.C. Age Norms on Leaving Home: Multilevel Evidence from the European Social Survey. Environ. Plan. A Econ. Space 2013 , 45 , 383–401. [ Google Scholar ] [ CrossRef ]
• Mulder, C.H. Family dynamics and housing: Conceptual issues and empirical findings. Demogr. Res. 2013 , 29 , 355–378. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Moreno Mínguez, A. The youth emancipation in Spain: A socio-demographic analysis. Int. J. Adolesc. Youth 2018 , 23 , 496–510. [ Google Scholar ] [ CrossRef ] [ Green Version ]
• Aparicio Fenoll, A.; Oppedisano, V. Fostering the Emancipation of Young People: Evidence from a Spanish Rental Subsidy. IZA Discuss. Paper 2012 , 6651 , 1–32. [ Google Scholar ] [ CrossRef ]
• Venhoda, O. Application of DSTI and DTI macroprudential policy limits to the mortgage market in the Czech Republic for the year 2022. Int. J. Econ. Sci. 2022 , 11 , 105–116. [ Google Scholar ] [ CrossRef ]
• Vandenbussche, M.; Verhenne, M. On the relation between unemployment and housing tenure: The European baby boomer generation. Master’s Thesis, Ghent University, Ghent, Belgium, 2014. Available online: https://lib.ugent.be/catalog/rug01:002164589 (accessed on 27 September 2022).
• Hromada, E.; Cermakova, K. Financial unavailability of housing in the Czech Republic and recommendations for its solution. Int. J. Econ. Sci. 2021 , 10 , 47–58. [ Google Scholar ] [ CrossRef ]
• European Commission. EPOV Member State Report–Spain ; Directorate-General for Energy: Spain, 2020; p. 4. Available online: https://energy-poverty.ec.europa.eu/discover/practices-and-policies-toolkit/publications/epov-member-state-report-spain_en (accessed on 27 September 2022).
• Mastropietro, P.; Rodilla, P.; Batlle, C. Emergency Measures to Protect Energy Consumers during the COVID-19 Pandemic: Global Review and Critical Analysis. Eur. Univ. Inst. 2020 , 4. [ Google Scholar ] [ CrossRef ] [ PubMed ]
• Borgersen, T.A. Social housing policy in a segmented housing market: Indirect effects on markets and on individuals. Int. J. Econ. Sci. 2019 , 8 , 1–21. [ Google Scholar ] [ CrossRef ]
• López-Rodríguez, D.; Matea Rosa, M.d.l.L. Public intervention in the rental housing market: A review of international experience. Doc. Ocas. del Banco de España 2020 , 2020 , 1–54. Available online: https://repositorio.bde.es/handle/123456789/13302 (accessed on 27 September 2022).

Click here to enlarge figure

Share and Cite

Mora-Garcia, R.-T.; Cespedes-Lopez, M.-F.; Perez-Sanchez, V.R. Housing Price Prediction Using Machine Learning Algorithms in COVID-19 Times. Land 2022 , 11 , 2100. https://doi.org/10.3390/land11112100

Mora-Garcia R-T, Cespedes-Lopez M-F, Perez-Sanchez VR. Housing Price Prediction Using Machine Learning Algorithms in COVID-19 Times. Land . 2022; 11(11):2100. https://doi.org/10.3390/land11112100

Mora-Garcia, Raul-Tomas, Maria-Francisca Cespedes-Lopez, and V. Raul Perez-Sanchez. 2022. "Housing Price Prediction Using Machine Learning Algorithms in COVID-19 Times" Land 11, no. 11: 2100. https://doi.org/10.3390/land11112100

Article Metrics

Article access statistics, further information, mdpi initiatives, follow mdpi.

Subscribe to receive issue release notifications and newsletters from MDPI journals

Boston housing price prediction case study in python

• Author Details

10 thoughts on “Boston housing price prediction case study in python”

Please add some videos on it which explain the steps one by one as you mentioned above.

Please keep updating the pages. Thanks once again for this.

Hi Ram! I am happy that these case studies are helpful to you! Videos are in progress. I will add them soon

Dear Mr Hashmi (Farukh), Thank You very much.

That was very beautiful and completely educational.

If you’ve written other case studies, please send me the address. Faithfully

Excuse me. I checked the main link of this page and i saw some other case studies there. It’s only to say Thanks and nothing else.

Thank you for the kind words! Please see below the link for all the case studies done in python. More will be uploaded soon! https://thinkingneuron.com/python-case-studies/

Dear Farukh, Thank you very much. Your model of expression is very informative and complete. Lessons and points are both reviewed and felt. wish you all the best …

Thank you for your kind words! I will add more of these very soon.

Hi Farukh, In this case, Chas and Rad were Categorical at first. In the middle of your analysis, suddenly Zn, considered as categorical and you … Please see the BoxPlots above. Why? Thanks

Hi leilazi,

Thank you for pointing this out! I have corrected the mistake 🙂

Liked your project, very helpful, please add some more projects from different domain like medical , finance etc…

Leave a Reply! Cancel Reply

Your email address will not be published. Required fields are marked *

• Data Science
• Data Analysis
• Data Visualization
• Machine Learning
• Deep Learning
• Computer Vision
• Artificial Intelligence
• AI ML DS Interview Series
• AI ML DS Projects series
• Data Engineering
• Web Scrapping

House Price Prediction using Machine Learning in Python

We all have experienced a time when we have to look up for a new house to buy. But then the journey begins with a lot of frauds, negotiating deals, researching the local areas and so on.

House Price Prediction using Machine Learning

So to deal with this kind of issues Today we will be preparing a MACHINE LEARNING Based model, trained on the House Price Prediction Dataset. 

You can download the dataset from this link.

The dataset contains 13 features :

Importing Libraries and Dataset

Here we are using 

• Pandas – To load the Dataframe
• Matplotlib – To visualize the data features i.e. barplot
• Seaborn – To see the correlation between features using heatmap

As we have imported the data. So shape method will show us the dimension of the dataset. 

Output: 

Data Preprocessing

Now, we categorize the features depending on their datatype (int, float, object) and then calculate the number of them. 

Exploratory Data Analysis

EDA refers to the deep analysis of data so as to discover different patterns and spot anomalies. Before making inferences from data it is essential to examine all your variables.

So here let’s make a heatmap using seaborn library.

To analyze the different categorical features. Let’s draw the barplot .

The plot shows that Exterior1st has around 16 unique categories and other features have around  6 unique categories. To findout the actual count of each category we can plot the bargraph of each four features separately.

Data Cleaning

Data Cleaning is the way to improvise the data or remove incorrect, corrupted or irrelevant data.

As in our dataset, there are some columns that are not important and irrelevant for the model training. So, we can drop that column before training. There are 2 approaches to dealing with empty/null values

• We can easily delete the column/row (if the feature or record is not much important).
• Filling the empty slots with mean/mode/0/NA/etc. (depending on the dataset requirement).

As Id Column will not be participating in any prediction. So we can Drop it.

Replacing SalePrice empty values with their mean values to make the data distribution symmetric.

Drop records with null values (as the empty records are very less).

Checking features which have null values in the new dataframe (if there are still any).

OneHotEncoder – For Label categorical features

One hot Encoding is the best way to convert categorical data into binary vectors. This maps the values to integer values. By using OneHotEncoder , we can easily convert object data into int. So for that, firstly we have to collect all the features which have the object datatype. To do so, we will make a loop.

Then once we have a list of all the features. We can apply OneHotEncoding to the whole list.

Splitting Dataset into Training and Testing

X and Y splitting (i.e. Y is the SalePrice column and the rest of the other columns are X)

Model and Accuracy

As we have to train the model to determine the continuous values, so we will be using these regression models.

• SVM-Support Vector Machine
• Random Forest Regressor
• Linear Regressor

And To calculate loss we will be using the mean_absolute_percentage_error module. It can easily be imported by using sklearn library. The formula for Mean Absolute Error : 

SVM – Support vector Machine

SVM can be used for both regression and classification model. It finds the hyperplane in the n-dimensional plane. To read more about svm refer this.

Output : 

Random Forest Regression

Random Forest is an ensemble technique that uses multiple of decision trees and can be used for both regression and classification tasks. To read more about random forests refer this.

Linear Regression

Linear Regression predicts the final output-dependent value based on the given independent features. Like, here we have to predict SalePrice depending on features like MSSubClass, YearBuilt, BldgType, Exterior1st etc. To read more about Linear Regression refer this.

CatBoost Classifier

CatBoost is a machine learning algorithm implemented by Yandex and is open-source. It is simple to interface with deep learning frameworks such as Apple’s Core ML and Google’s TensorFlow. Performance, ease-of-use, and robustness are the main advantages of the CatBoost library. To read more about CatBoost refer this .

Clearly, SVM model is giving better accuracy as the mean absolute error is the least among all the other regressor models i.e. 0.18 approx. To get much better results ensemble learning techniques like Bagging and Boosting can also be used.

Please Login to comment...

Similar reads, improve your coding skills with practice.

What kind of Experience do you want to share?

IEEE Account

• Change Username/Password
• Update Address

Purchase Details

• Payment Options
• Order History
• View Purchased Documents

Profile Information

• Communications Preferences
• Profession and Education
• Technical Interests
• US & Canada: +1 800 678 4333
• Worldwide: +1 732 981 0060
• Contact & Support
• About IEEE Xplore
• Accessibility
• Terms of Use
• Nondiscrimination Policy
• Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

Academia.edu no longer supports Internet Explorer.

To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to  upgrade your browser .

Enter the email address you signed up with and we'll email you a reset link.

• We're Hiring!
• Help Center

House Price Prediction

2018, Comparison of Data Mining Models to Predict House Prices

Buying a house is commonly the most important financial transaction for the average person. The fact that most prices are negotiated individually (unlike a stock exchange system) creates an environment that results in an inefficient system. Most people buying houses are inexperienced amateurs with limited information about the market. A housing bubble cannot exist if individuals are making rational decisions. The objective of this paper is to evaluate the performance of a stacked regression model compared to several sub models based on predicting house prices. House characteristics and the final house price was gathered from King County, Washington, USA during the period of May 2014 and May 2015. The observed result indicates that combining the sub algorithms using a general linear model did not significantly improve results.

Related Papers

International Journal of Engineering Applied Sciences and Technology

Aadesh Mallya

The housing market is a standout amongst the most engaged with respect to estimating the price and continues to vary. Individuals are cautious when they are endeavoring to purchase another house with their financial plan and market strategies. Consequently, making the housing market one of the incredible fields to apply the ideas of machine learning on how to enhance and anticipate the house prices with precision. The objective of the paper is the prediction of the market value of a real estate property and present a performance comparison between various regression models applied. Nine algorithms were selected to predict the dependent variable in our dataset and then their performance was compared using R2 score, mean absolute error, mean squared error and root mean squared error. Moreover, this study attempts to analyze the correlation between variables to determine the most important factors that are bound to affect the prices of house.

International Journal for Research in Applied Science & Engineering Technology (IJRASET)

IJRASET Publication

The housing sector is the second-largest employment provider after the agriculture sector in India and is estimated to grow at 30% over the next decade. Housing is one of the major sectors of real estate and is well complemented by the growth of urban and semi-urban accommodations. Ambiguity among the prices of houses makes it difficult for the buyer to select their dream house. The interest of both buyers and sellers should be satisfied so that they do not overestimate or underestimate the price. Our system provides a decisive housing price prediction model to benefit a buyer and seller or a real estate agent to make a better-informed decision system on multiple features. To achieve this, various features are selected as input from the feature set and various approaches can be taken such as Regression Models or ANN.

INTERNATIONAL JOURNAL OF ADVANCE RESEARCH, IDEAS AND INNOVATIONS IN TECHNOLOGY

Ijariit Journal

The prices of House increases every year, so there is a need for the system to predict house prices in the future. House price prediction can help the developer to determine the selling price of a house. It also can help the customer to arrange the right time to purchase a house. There are some factors that influence the price of a house which depends on physical conditions, concept, location and others. House prices vary for each place and in different communities. There are various techniques for predicting house prices. One of the efficient ways is by the use of the regression technique. Regression is a reliable method of identifying which variables have an impact on a topic of interest. Random forests are very accurate and robust to over-fitting. The process of performing a regression allows to confidently determine which factors matter the most, which factors can be ignored and how the factors influence each other. The main objective is to use an advanced methodology for prediction.

IJIRT Journal

House price forecasting is an important topic of real estate. The literature attempts to drive useful knowledge from historical data of property markets. Machine learning techniques are applied to analyze historical property transaction to discover useful models for house buyers and sellers. Revealed is the high discrepancy between house prices in the most expensive and most affordable suburbs. Moreover, experiments demonstrate that the combination of stepwise and support vector machine that is based on mean squared error measurement is a competitive approach. The goal of the study is through analyzing a real historical transactional dataset to derive valuable insight into the housing market. It seeks useful models to predict the value of a house given a set of its characteristics. Effective model could allow home buyers or real estate agents to make better decisions.

International Journal of Scientific Research in Computer Science, Engineering and Information Technology

International Journal of Scientific Research in Computer Science, Engineering and Information Technology IJSRCSEIT

The goal of the paper is to help prospective homeowners make well-informed selections that take into account their finances and market trends. It attempts to forecast house prices for those who do not own a home by examining their financial plans and goals. Various regression techniques, such as Linear Regression and Decision Tree Regression, are employed to estimate speculated prices. The analysis involves assessing the accuracy and R2 score values of the predictions using relevant data. The study's objective is to determine the most effective regression technique for house price prediction. The ultimate objective is to assist sellers in accurately calculating the price at which to sell a home and to assist buyers in determining when it is best to make a real estate acquisition.

International Journal of Scientific & Technology Research

Ayush Sharma

With the booming civilization and ever-changing market requirements, it is essential to know the market drifts. Today prediction of house prices according to the trends is the principal essence of the study. It is imperative for an individual to understand the business trends so that he can prepare his budgetary needs according to his requirements. Real Estate is an ever-growing enterprise with an expanding society. For an investor, it is essential to comprehend the business drifts, which can assist him to underwrite in the right way and augment his business throughput. Sometimes clients get dupe by the hoax market rate set up the agent due to which the real estate industry is less translucent these days. With an uptick in convince of the dataset, it's viable for a researcher to develop a model with high accuracy. The previous model with decreased accuracy and overfitting of data reduces the efficiency, whereas the proposed system resolves such issues and provides a better and e...

International Journal of Modern Education and Computer Science

Ismail Ibrahim

Procedia Computer Science

Minh Kim Thu Nguyen

Amity Journal of Computational Sciences (AJCS)ISSN: 2456-6616 (Online) 18 www.amity.edu/ajcs

Anurag Sinha

Machine learning participate a significant role in every single area of technology as per the today's scenario. Even I can Say every phase of our lives is surrounded by the implementation of new era technologies such as Hospitality management, Railway, Transportation, Health care, Industry And so on. Machine learning has been employed for many sectors since past decades like image processing, pattern recognition, medical diagnosis, and predictive analysis, product recommendation. House prices changes every year, so it is mandatory for a structure to foresee house prices in the future. House price prediction can help in fixing and thereby predicting house prices and customer can evaluate it. Our intension is to predict house prices using several machine learning techniques. House price of particular location does depends on various factors like lotsize, bedrooms, bathrooms, location, drawing room, material used in house , interiors, parking area and mainly on square feet per area. Our intension behind proposing this paper is to employ different machine learning techniques for predicting the price based on these metrics. The algorithm used in this analysis is Data refining, OLS regression, Classification, Clustering, correlation matrix.

WARSE The World Academy of Research in Science and Engineering

The increasing and decreasing occurrence of house prices changes from time to time. There are more reasons that effect the fluctuation of house prices. Some are build year, location, physical amenities, size of house etc. Predicting the value of house (Sale price) helps the customers to take right choice of buying the house. Machine learning is being adapted for various fields that could build prediction model and estimate the outcomes. In this paper, we are contemplating the issue of rise and fall of house rates as a regression problem. Regression is a process that aims to predict the correlation between target dependent feature and a sequence of other changing independent features. In our experimental analysis, we are using Decision Tree Regression, Linear Regression, Ada Boost Regression, Gradient Boost Regression, Random Forest Regression techniques. In addition, we are also used AutoML to predict the House sale price. AutoML is a system that takes labelled trained data as input and automatically build a suitable optimized model that the dataset fits.

Loading Preview

Sorry, preview is currently unavailable. You can download the paper by clicking the button above.

RELATED PAPERS

hamed tohidi

International Journal for Research in Applied Science and Engineering Technology

sonia juneja

International Journal of Advanced Computer Science and Applications

Sofianita (Dr) Mutalib

International Research Journal on Advanced Science Hub

Tanmoy Dhar

IRJET Journal

International Journal of Research Publication and Reviews

Ankit Pati Tripathi

International Journal of Scientific Research in Science and Technology

International Journal of Scientific Research in Science and Technology IJSRST

Suraya Masrom

IOP Conference Series: Materials Science and Engineering

Shubham Jain

Haziq Izhar Kun

2015 2nd IEEE International Conference on Spatial Data Mining and Geographical Knowledge Services (ICSDM)

Kelvyn Jones

Zenodo (CERN European Organization for Nuclear Research)

Sweety Jachak

International Journal of Strategic Property Management

Adela Deaconu

International Journal For Multidisciplinary Research

AYUSH DAVE , Krish Shah

Michael Sklarz

OMAR ARMANDO ROJAS SIERRA

International Journal of Innovative Technology and Exploring Engineering

Rahul Chawda

RELATED TOPICS

•   We're Hiring!
•   Help Center
• Find new research papers in:
• Health Sciences
• Earth Sciences
• Cognitive Science
• Mathematics
• Computer Science
• Academia ©2024

• DOI: 10.14569/ijacsa.2021.0121291
• Corpus ID: 245623192

Advanced Machine Learning Algorithms for House Price Prediction: Case Study in Kuala Lumpur

• S. Abdul-Rahman , Nor Hamizah Zulkifley , +1 author Sofianita Mutalib
• Published in International Journal of… 2021
• Computer Science, Economics, Business

8 Citations

The effect of security in the green building price prediction model: a comparison between multiple linear regression and machine learning approaches, rent price prediction with advanced machine learning methods: a comparison of california and texas, comparative analysis of machine learning algorithms for predicting dubai property prices, house base-price prediction with machine learning methods, multiedge graph convolutional network for house price prediction, temperature prediction of once-through steam generator tubes based on neural network, real-estate price prediction with deep neural network and principal component analysis, a machine learning method for real estate operation projects forecasting, related papers.

Showing 1 through 3 of 0 Related Papers

• Countertops
• Curb Appeal
• Dining Rooms
• Entryways & Mudrooms
• Foundations
• Heating & Cooling
• Home Finances
• Home Offices
• Home Safety
• Inspections
• Kids' Rooms
• Landscaping
• Laundry Rooms
• Living Rooms
• Molding & Trim
• Natural Disasters
• Pathways & Sidewalks
• Pest Control
• Smart Homes
• Solar & Alternative Energy
• Storage & Organization
• Woodworking
• This Old House
• Ask This Old House
• New Yankee Workshop
• Project Houses
• Idea Houses
• Live Channel
• TV Listings
• Ways to Watch
• Best Gutter Guards
• Best Home Warranty
• Best Lawn Care
• Best Window Brands
• Best Moving Companies
• Best Solar Companies
• Newsletters
• Makers Channel

What Affects Mortgage Rates?

Selling a home, buying a home, is now a good time to refinance a house, tips for buying a house, our conclusion, will mortgage rates finally go down in 2024.

Written by Taelor Candiloro Updated 03/06/2024

Taelor Candiloro leverages a degree in anthropology from Utah State University to bring data-driven clarity and nuance to trends in personal finance and the housing market. They are particularly interested in how data can support efforts to highlight and address structural inequity. When they ar…

As the Federal Reserve monitors slowing inflation and holds interest rates steady, many experts predict that mortgage rates will go down in 2024. While the high interest rates of the past year kept prospective buyers out of the market, lower rates in 2024 could bring them back.

Before you buy a new home and call a moving company , let’s explore what lower mortgage rates could mean for homebuyers. Our team consulted experts in real estate and finance who offered predictions and insights on the 2024 market.

What Do Experts Predict for Mortgage Rates in 2024?

The Federal Reserve is the central bank of the U.S., so it works to minimize unemployment and keep the financial system stable. Inflation, which is the general increase in prices and decrease in the purchasing value of money, ideally rises no more than 2% per year .

When inflation rises too fast, as it has recently, the Fed increases interest rates. This is meant to promote less spending and decrease demand as people and businesses take out fewer loans. A higher interest rate should slow the economy while a lower interest rate encourages greater spending.

The Fed doesn’t set mortgage rates but controls the federal funds rate, an interest rate that banks pay for short-term loans. When the Fed changes the rate paid to banks on reserve balances, financial institutions adjust other interest rates such as for mortgages.

Inflation has slowed considerably from a high of 9.1% in June 2022 to 3.1% in January 2024. In addition to the Fed’s policy, other factors could be responsible for this decrease. Recessions in other countries, global conflicts, and presidential elections all contribute to economic uncertainty. While the Fed hasn’t significantly lowered interest rates yet, experts believe that rates are likely to fall in the next few months.

Note that the lowest posted mortgage interest rate isn’t available to everyone. Mortgage rates for individuals depend on factors such as their credit score and the percent down payment they can offer. Rates will likely vary by financial institution, so we recommend comparing them across banks, credit unions, and mortgage brokers.

What Does This Mean for Prospective Buyers?

Is now the right time to buy or sell a home? Prospective buyers should ask whether they need to get out of an existing mortgage, how long they plan to stay in the new house, and if they’re willing to wait for rates to decrease further.

Homeowners who bought in the last decade likely benefited from lower mortgage rates, making them hesitant to sell their houses. However, lower rates could make selling more tempting in 2024.

“Lots of people had mortgages at around 3% when rates went up to 7%,” Van Order said. “They were locked into their current house because they would have to give up their low-rate mortgage if they sold their house. This cut into houses available for sale, which kept prices up.” Van Order predicted that this trend could reverse itself depending on how far rates drop.

Other experts predicted that greater availability of inventory could lead to higher prices. Tysiak thought that lower interest rates would lead consumers to pay higher monthly payments and get approved for higher loans.

“With interest rates falling, homes that are higher in price should see additional competition because more buyers are now able to afford the home,” Tysiak said. “If you’re a buyer, expect to pay a higher price.”

Because people tend to buy at the top of their budgets, Tysiak expected home prices to rise. Lower interest rates may encourage sellers who were on the fence about moving to jump at the opportunity to cash in on their houses and take on new mortgages elsewhere.  “A seller is more likely to sell when they can get a higher price for their house,” Tysiak said.

Our 2024 Aspiring Homeowners Report indicates that buyers are eager to enter the market. Nearly one-third (30%) of potential homebuyers we surveyed would settle for a mortgage rate higher than 6% if it meant being able to pursue homeownership. So, what do prospective homebuyers need to know about 2024 mortgage rates and how they’ll affect the housing market?

With more sellers putting homes on the market, inventory may rise. This means that prospective buyers will be competing for inventory with sellers looking for new homes. While builders could be encouraged to create new supply, prices will likely go up as sellers previously locked into low mortgage rates get more willing to buy new houses.

Van Order, who predicted a competitive housing market in 2024, said the stagnation caused by sellers locked into low mortgage rates “has made the market less competitive by limiting supply, but that should diminish as rates fall and supply increases.” Van Order also said that the housing market should expand as “low borrowing costs make financing a house less costly, which steps up homebuying and production.” In other words, institutional builders may take advantage of cheaper credit and produce more housing.

Sandy Bond, professor of practice in real estate at Bucknell University, believed that interest rate drops in 2024 wouldn’t be sufficient to cause major movement in the real estate market.

“Typically, a rate drop would entice buyers into the market, but it would need to drop significantly (more than the predicted Fed adjustments of 0.25 basis points) to have any noticeable impact,” Bond said.

Bond predicted that falling inflation levels and improved consumer purchasing power wouldn’t cause a real estate gold rush. “I believe the housing market will stay relatively stable for 2024,” she said. Bond explained that homeowners locked into 30-year mortgages at low-interest rates are “unlikely to want to give up such favorable terms by purchasing a new home.”

Slightly lower rates probably won’t encourage buyers with competitive mortgage rates to refinance. However, for buyers who bought at peak interest rates, refinancing at a lower rate could result in a reduced monthly payment and a lower amount paid in interest over time.

Other reasons for homeowners to refinance include freeing up equity for a major purchase or for remodeling an existing home. Refinancing could appeal to those who need more space but don’t want to move into a completely new house.

The Mortgage Bankers Association is seeing indicators that rates below 7% are resulting in an increase in home loan refinancing applications . Common wisdom says that refinancing may be worth it if you can lower your interest rate by at least 1%. If you’re considering refinancing, look out for hidden costs. Refinancing isn’t free, and closing costs, along with other fees, could significantly cut into your savings.

Refinancing from a fixed-rate mortgage to an adjustable-rate mortgage (ARM) with much lower interest may offer immediate benefits but could lead to higher payments if rates go back up.

Make sure to carefully prepare before buying a home. Below are a few steps that buyers can take to get ready for a home purchase:

• Get preapproved for a mortgage loan. “Getting preapproved for a loan helps in a competitive lending market,” Bond said. Start shopping for a lender before you’ve found your dream home since a preapproval letter is usually required when making an offer.
• Check your credit rating at the three main credit bureaus: Experian, Equifax, and TransUnion. If your credit score is below 600, it could affect the interest rate a lender is willing to give you. To improve credit, pay all outstanding bills and contact the lender if you’ve fallen behind on credit card payments. Use only 30% of your available credit if possible and keep older lines of credit open to demonstrate a longer credit history.
• Assess your financial situation before committing to a mortgage. Consider whether your budget can sustain the monthly costs of owning a home. “Homeownership comes with mortgage payments, property taxes, homeowners insurance, maintenance, and repairs,” Tysiak said. “Developing a budget is essential in determining how much the buyer can actually afford.”
• Don’t rule out an adjustable-rate mortgage (ARM) instead of a fixed-rate mortgage. Although these mortgages start with a teaser rate that could increase during the life of a loan, they could be a decent option for certain homebuyers.
• To lower your interest rate, make the maximum possible down payment. “Putting down 20% of the purchase price will allow the buyer to avoid private mortgage insurance (PMI), which could be several hundred more dollars per month,” Tysiak said.
• Consider a down payment program. Down payment assistance programs help buyers get money for either a down payment or closing costs. These loans or grants are often provided through government- or community-sponsored programs but can also be received from mortgage companies. Our aspiring homeowners report found that 76% of respondents plan to use a down payment program when they purchase their first home.

While it’s unclear how much interest rates will go down in 2024, any meaningful decrease could stimulate extra movement in the housing market. Whether you’re a first-time homebuyer or a seller waiting for the right moment to list your house, being aware of 2024 interest rate trends can give you an educated decision about when to move.

Our Experts

Advertiser Disclosure

Our editorial team is committed to creating independent and objective content focused on helping our readers make informed decisions. To help support these efforts we receive compensation from companies that advertise with us.

The compensation we receive from these companies may impact how and where products appear on this site. This compensation does not influence the recommendations or advice our editorial team provides within our content. We do not include all companies, products or offers that may be available.

• Share full article

For more audio journalism and storytelling, download New York Times Audio , a new iOS app available for news subscribers.

Harris Chooses Walz

A guide to the career, politics and sudden stardom of gov. tim walz of minnesota, now vice president kamala harris’s running mate..

This transcript was created using speech recognition software. While it has been reviewed by human transcribers, it may contain errors. Please review the episode audio before quoting from this transcript and email [email protected] with any questions.

Hey, it’s Michael. Before we get started, I want to tell you about another show made by “The New York Times” that pairs perfectly with “The Daily.” It’s called “The Headlines.” It’s a show hosted by my colleague, Tracy Mumford, that quickly catches you up on the day’s top stories and features insights from “The Times” reporters who are covering them, all in about 10 minutes or less.

So if you like “The Daily”— and if you’re listening, I have to assume you do — I hope that means you’re going to “The Headlines” as well. You can now find “The Headlines” wherever you get your podcasts. So find it, subscribe to it, and thank you. And now, here’s today’s “Daily.”

From “The New York Times,” I’m Michael Barbaro. This is “The Daily.”

[MUSIC PLAYING]

Today, the story of how a little known Midwestern governor became Kamala Harris’s choice for a running mate. My colleague Ernesto Londoño walks us through the career, politics, and sudden stardom of Governor Tim Walz of Minnesota.

It’s Wednesday, August 7.

Ernesto, over the past few days, we watched Vice President Harris bring the final three contenders for her running mate to her house in Washington, DC, for a set of in-person interviews. And then we watched as she seemed to narrow her pool of choices down to a final two — the governor of Pennsylvania, Josh Shapiro, and the governor of Minnesota, Tim Walz. And now, of course, we know that she has made her choice. What has she told us about her campaign strategy, the way she views this race, in ultimately choosing Tim Walz?

Michael, I think what the choice tells us is that Kamala Harris was drawn to two qualities that Governor Walz brings to the table. And what’s interesting is they may seem to be in tension. For starters, here’s the ultimate everyday man, somebody who grew up in a small town in Middle America, served in the National Guard, was a high school teacher, a football coach, very plain-spoken, goes to campaign events wearing T-shirts and baseball caps, is a gun owner and very proud about it. He sort of embodies the Midwest.

And she clearly thinks that that is going to bring the kind of moderate, white, working class voters that the campaign needs in swing states to come to them, to make this feel like a balanced ticket and something that will give her enough of the crucial votes to defeat Donald Trump in the fall.

On the other hand, as governor, he passed a slew of pretty progressive legislation in the past couple of years, everything from abortion rights to gun control. So these things are likely to appeal to bread and butter Democrats.

But the question is, when voters have examined these two facets of Tim Walz, may it bring them enough enthusiasm from the base and enough undecided voters that the campaign desperately needs, or at some point, do these two aspects of him start canceling each other out?

Right. In short, you’re saying Harris is betting on a dual appeal from Walz to two essential constituencies, but the risk is that the appeal to one of them is just much, much greater than to the other.

Right. You could definitely see a scenario where voters, once they’ve examined Tim Walz’s story and legacy, may conclude that both of these candidates are quite liberal.

OK, so tell us the story of Tim Walz, a story that I think a lot of us don’t know because we really don’t know Walz all that well, and how he has come to embody these two qualities and that tension that you just described.

Michael, the origin story of Tim Walz’s political career is quite fascinating.

He and his wife were teachers in a small city south of Minneapolis. And in 2004, when George W. Bush was running for re-election, Walz took a group of his students to a political rally in his hometown. They wanted to just see the president make his case. And a strange scuffle happened when they were trying to get in.

Well, one of the kids had a John Kerry sticker on his wallet. And this is where the individual says, well, you’re not going to be allowed to enter. You’ve been deemed a threat.

Apparently, one of the students had a sticker for Bush’s rival, John Kerry, on his wallet. And security officials at the rally didn’t want to let them in.

And I said, oh, it’s OK. They’re with me. And who are you? And I said, I’m Tim Walz. I’m their teacher here, and showed them my ID. And they said, well, you two have been deemed a threat to the president. And I said, well, that’s not true. And it kind of escalated.

And this really ticked off Tim Walz. He was really upset. There was a fight and a confrontation at the rally.

At this point in time, I’m kind of nervous. I’m getting arrested. So I’m like saying, well, I’m Teacher of the Year in Mankato. And they didn’t care about that. And it was kind of a sad epiphany moment, how it felt for people to be looked right through by people. These people didn’t see me. And this is happening.

And ultimately, he sort of walks away from this moment feeling really sick of the Bush administration, the politics of the day. And he turns around and volunteers for the Kerry campaign.

And then the more interested he becomes in politics in this era, he starts looking around his congressional district, and there’s a Republican who’s held the seat for many, many years. This was a largely rural district in southern Minnesota. And there’s no reason to believe that a newcomer to politics, somebody without a donor base, could make a run for this seat and win.

But Walz signs up for this weekend boot camp, where expert campaigners train newcomers who want to run for office. And he gets really enthused by the idea that he can pull it off. So he starts raising money with the support of an army of students who become so thrilled and energized by the prospect that their nerdy and kind geography teacher is making this uphill bid for a congressional race.

So his campaign staff is basically his former students.

That’s right. And he proves to be a formidable candidate. He draws a lot of attention to his experience in the classroom and as a coach.

When I coached football, these stands held about 3,000 people. That’s a lot. It’s also the number of American soldiers who have died fighting in Iraq.

He’s a very strong advocate for pulling out of the war in Iraq.

Serving right now are kids that I taught, coached, and trained to be soldiers. They deserve a plan for Iraq to govern itself, so they can come home.

And one thing that happens in the campaign that is really surprising to people is he comes out as being in favor of same-sex marriage. Now, it’s useful to remember that this is 2006, when the vast majority of Democrats, Democrats running for most elected office, were not ready to come out in favor of same-sex marriage.

And here’s a guy who’s new to politics, who’s trying to unseat a Republican who’s held on to his seat for more than 12 years, taking what appeared to be a reckless position on something. And when he was asked about it at the time, Tim Walz told a supporter, this just happens to be what I believe in. And I’d rather lose a race that I’ve ran being true and consistent to my values than try to run as somebody I’m not.

And of course, he wins.

Yes. To everybody’s surprise, he pulled it off.

So from the get-go, he shows a kind of maverick, “politics be damned” quality, taking stands that he knows may be unpopular among the voters he’s trying to win over. But he’s got some innate political gifts that are all making it work.

Yeah, I think that first campaign showed us that Tim Walz had real political chops. He was a very effective campaigner. And people really liked him. When he was knocking on doors, when he was introducing himself to voters, they saw him as somebody who was very genuine and who was admirable.

So once he gets elected in this conservative leaning district in Minnesota, what does he actually do in Congress?

In Congress, he develops a reputation for being somebody who can work across the aisle. And this is a period where Democrats and Republicans were deeply polarized over the Iraq War. He spends a lot of his time lobbying to expand benefits for veterans, so it’s easier for them to go to college after their service, and also becomes a leading voice in the quest to repeal Don’t Ask, Don’t Tell, the policy that prohibited openly gay servicemen from serving in uniform.

And he remained really popular. He easily won re-election five times. The last time he runs for his seat happens to be 2016, when President Trump wins his district by about 15 points.

And still, voters kept Tim Walz in office.

I think it’s important to note what you just said. Walz is distinguishing himself as a Democrat who can take some pretty progressive positions, as he did in that first campaign on gay rights, as he did with Don’t Ask, Don’t Tell, and keep winning in very Trump-friendly districts of his state.

That’s right. And as he’s serving his sixth term in office, he sets his sights on the governor’s mansion and decides to run for office in 2018. He wins that race easily. And early on, during his time as governor, the eyes of the world are on Minnesota after a police officer kills George Floyd. And what we see is massive looting and protests in Minneapolis.

Right, and remind us how Governor Walz handles that violence, those protests.

Yeah, I think that’s a crucial chapter in Tim Walz’s political career and one that will come under scrutiny in the days ahead.

After George Floyd was killed on a Monday —

People are upset, and they’re tired. And being Black in Minnesota already has a stigma and a mark on your back.

— protests took root in Minneapolis.

Y’all want to sit out here and shoot off your rubber bullets and tear gas.

And they got progressively larger and more violent.

There comes a point where the mayor and the police chief in Minneapolis plead for help. They ask the governor to send in the National Guard. And crucially, that request was not immediately heeded.

This is the third precinct here. There are fires burning to the left of it at the —

And at the height of the crisis, a police precinct building was abandoned.

There’s someone climbing up the wall right now, kicking the window in, trying to climb up the wall.

Because city officials grew concerned that protesters were about to overrun it and may attack the cops inside their own turf.

[EXPLOSIONS]

And the building is set on fire.

Right, a very memorable image. I can recall it happening in real-time.

Yeah, and in the days that followed, I think there were a lot of questions of why the governor didn’t send in troops earlier and whether a more muscular, decisive response could have averted some of the destruction that spread through the city.

And how does Walz end up explaining his decision not to send in the National Guard more quickly?

The governor and his administration have said that they were really, really dealing with an unprecedented challenge. And I think there was a concern that sending in troops into this really, really tense situation could have done more to escalate rather than pacify things on the street.

But in the weeks and months that followed, there were a lot of questions about Governor Walz’s leadership. And there were critics who said, during what may have been the most challenging week of his life, we saw a governor who was indecisive and who waited too long to send in resources that ultimately allowed the city to get to a semblance of order.

Right, and it feels like this is a moment that will almost assuredly be used against him by Donald Trump and JD Vance, the Republican ticket, which has made law and order so central to their message in this campaign.

Yeah, absolutely. And here in Minnesota, that was certainly a liability for him when he ran for re-election in 2022. But voters kept him in office, and he won that race handily. And not only did he win, but Democrats managed to flip the Senate and have full control of the legislature on his watch.

And that sets in motion one of the most productive legislative sessions in Minnesota history, where Tim Walz and his allies in the House and the Senate managed to pass a trove of really progressive legislation, oftentimes on a party vote.

Tell us about some of that legislation.

Well, Minnesota becomes the first state in the wake of the Supreme Court ending the constitutional right to abortion to actually codify this right under state statute. And they did a lot more stuff. They had a huge budget surplus, and they used that, for instance, to fund meals for all school children.

They managed to pass a couple of gun control laws that were very contentious. They gave the right to undocumented immigrants to get driver’s licenses. They legalized recreational marijuana. And finally, the governor takes a pretty bold stance on this issue of gender affirming care for transgender kids and teenagers, and says that Minnesota will be a safe haven for people who want that health care.

So, Ernesto, so how should we think about that blitz of legislation and the largely progressive tone of it, given the way that Walz had campaigned and succeeded up to that moment as somebody with such broad appeal across the political spectrum?

When the governor was asked whether this had been too much too quickly in terms of progressive legislation, his answer was that these were broadly popular policies, that these are issues Democrats had campaigned on. And here, Democrats had a window of opportunity where they were in control of the governor’s mansion and control of the House, the Senate, and that when you have political capital, you spend it.

But when you start listening to Republicans in Minnesota, they say, here’s a guy who campaigned on this mantra of “One Minnesota.” That was his campaign slogan. And he sort of came into office with this promise that he would govern in a bipartisan way, reach across the aisle.

But when they had all the votes they needed to pass their policies, Republicans felt that Walz was not bothering to bring them into the fold and to pass legislation that was going to be palatable to conservatives in the state. So I think people who once regarded him as a moderate now start seeing him as somebody who, when he had the power, acted in ways that were really progressive and liberal.

So at the height of his power, Governor Walz emerges as somebody who, when given a shot at getting done what he really wants to get done with a Democratic legislature, is a pretty progressive leader, even at the risk of being somewhat at odds with his earlier image as more moderate, because in his mind, enough people in the state are behind these policies.

Yeah, and I think he assumed that he had banked enough goodwill and that people across the state liked him enough to tolerate policies they may have disagreed with. And I think it’s safe to say, among the people who cover him here regularly, there was never any real hint that Tim Walz was eyeing a run for higher office. He’s not somebody who has written the kind of political memoir that oftentimes serves as a case of what you would bring to a national ticket or to the White House. And he seems pretty happy with a state job.

So it was a huge surprise when Tim Walz starts going viral through a string of cable news appearances right after President Biden drops out of the race, and the Democrats are scrambling to put Harris at the top of the ticket. And what becomes clear is that Walz is very forcefully auditioning for the role of vice president, and Vice President. Harris starts taking him very seriously.

We’ll be right back.

So, Ernesto, tell us about this cable news audition that Governor Walz undertakes over the past few weeks and how, ultimately, it seemed to help him land this job of being Harris’s running mate.

I think Walz does something really interesting, and that is that he says that Democrats shouldn’t be talking about Trump and Vance as existential threats. He kind of makes the case that Democrats have been in this state of fear and paralysis for too long, and that it’s not serving them well. So the word he latches onto is “weird.”

Well, it’s true. These guys are just weird.

It is. It is.

And they’re running for he-man women hater’s club or something. That’s what they go at. That’s not what people are interested in.

And I think one other thing we see in Walz is somebody who’s putting himself out there as a foil to JD Vance.

That angst that JD Vance talks about in “Hillbilly Elegy,” none of my hillbilly cousins went to Yale, and none of them went on to be venture capitalists or whatever. It’s not —

I think the case he’s making is that Tim Walz is a more authentic embodiment of small town values.

What I know is, is that people like JD Vance know nothing about small town America. My town had 400 people in it, 24 kids in my graduating class. 12 were cousins. And he gets it all wrong. It’s not about hate.

And behind the scenes, people from Tim Walz’s days on Capitol Hill start calling everybody they know in the Harris campaign and the Harris orbit and saying, here’s a guy who has executive experience as governor, but also somebody who has a really impressive record from his time on Capitol Hill and somebody who could be an asset in helping a Harris administration pass tough legislation. So you should take a hard look at this guy.

Which is, of course, exactly what Harris ends up doing. And I want to talk for a moment about how Harris announces Walz as her running mate on Tuesday morning. She did it in an Instagram message. And it felt like the way she did it very much embraced this idea that you raised earlier, Ernesto, that Walz contains these two appeals, one to the Democratic base, one to the white working class.

Harris specifically cites the work that Walz did with Republicans on infrastructure and then cites his work on gun control. She mentions that he was a football coach and the founder of the high school Gay Straight Alliance. She’s straddling these two versions of Walz.

But I want to linger on the idea for a moment of Walz’s vulnerabilities, because once he becomes Harris’s running mate, Harris and Walz are going to lose a fair amount of control over how they present him to the country, because he’s going to become the subject of very fierce attacks from the Republicans in this race. So talk about that for just a moment.

Yeah, I mean, it’s important to keep in mind that Governor Walz has never endured the scrutiny of a presidential race. So the questions he’s going to be asked and the way his record is going to be looked at is going to be different and sharper. I think the Harris campaign is billing him as, first and foremost, a fighter for the middle class. And I think that certainly will have some appeal.

But I think in coming days, there’s going to be a lot of attention drawn to parts of his record that may be unpopular with many voters. For instance, giving undocumented immigrants driver’s licenses, which Governor Walz championed. It’s likely to provide fodder for an attack ad.

The very dramatic footage of Minneapolis burning in 2020 is also something that I think people will be drawn to. And there’s going to be interest in reexamining what the governor did and what he could have done differently to avert the chaos.

And on Tuesday, we saw that the Trump campaign wasted no time in trying to define Tim Walz as soft on crime, permissive on immigration policy. And they also made clear they wanted to relitigate the era of George Floyd’s killing. And specifically, they want to try to tie him to the effort at the time to defund the police, which is a movement that Walz personally never endorsed.

So the Republican attack here will be pretty simple. Walz is liberal. Harris is liberal. So, in their efforts to speak to especially white working class and rural voters in swing states, the Trump campaign is going to say this is not the ticket for that group of voters. This is the ticket of burning police precincts and gun control. And of course, that may not be fair, but that’s very likely going to be the message over the next couple of months.

Right. I think there’s going to be effort to portray him as a radical liberal who has used his small town roots to put on this sort of veneer of being a moderate and a really sort of understanding and being part of the segments of the electorate that I think are critical in this election.

I want to speak for just a moment about the person Harris did not pick when she chose Walz because many Democrats had felt that Walz was a potentially too liberal seeming running mate for a candidate, Kamala Harris, who herself comes from a blue state and is caricatured by the Republicans as liberal herself.

And the person she didn’t choose was Governor Josh Shapiro of Pennsylvania, who was seen as having a huge appeal in that particular key swing state, but also presented risks of his own of alienating parts of the Democratic base with his well-documented support for Israel and his criticism of campus protesters. How should we think about the fact that, ultimately, Harris chose Walz over Shapiro?

Yeah, I think in the final stretch of this campaign to be the vice presidential pick, we started seeing a lot of acrimony in pockets of the Democratic base, drawing attention to the fact that Governor Shapiro could be divisive on Gaza, which has really sort of split the party in recent months.

So I think at the end of the day, they made a calculation that Tim Walz would be more of a unifying figure and would be somebody who would inspire and energize enough pockets of the electorate that they need, particularly in the Midwest, to make him the stronger and more exciting pick and somebody who wouldn’t force them to go back to defending and relitigating the Biden administration’s record on Israel and on the war in Gaza.

Right, and then, on Tuesday night, we got our first glimpse of Harris and Walz together on stage for the first time at a campaign rally. I’m curious, what struck you about their debut together.

Good evening, Philadelphia.

I think everybody was watching the opening scene of this rally to see what the chemistry between these two people was going to be like. And they both seemed giddy. They were literally, at times, bouncing with enthusiasm.

Since the day that I announced my candidacy, I set out to find a partner who can help build this brighter future.

So Pennsylvania, I’m here today because I found such a leader.

Governor Tim Walz of the great state of Minnesota.

They soon got down to business. And that business was how to define Tim Waltz for voters who don’t know him well.

To those who know him best, Tim is more than a governor.

And right off the bat, we saw that Kamala Harris really highlighted a lot of pieces of his pre-political career.

To his former high school football players, he was Coach.

She repeatedly called him Coach Walz, Mr. Walz, evoking his time in the classroom, and even used his military title from his days in the Army.

To his fellow veterans, he is Sergeant Major Walz.

And then when it came time for Tim Walz to introduce himself on this massive stage —

Welcome the next vice president of the United States, Tim Walz.

— he drew a lot of attention to his small town roots.

I was born in West Point, Nebraska. I lived in Butte, a small town of 400.

He said something that he said repeatedly recently in campaign appearances, which is —

In Minnesota, we respect our neighbors and their personal choices that they make. Even if we wouldn’t make the same choice for ourselves, there’s a golden rule — mind your own damn business.

The golden rule of small towns is you mind your own damn business, which is something he said in the context of his argument that Republicans have been limiting, rather than expanding, people’s rights. But he also drew attention to the fact that he’s a gun owner.

By the way, as you heard, I was one of the best shots in Congress. But in Minnesota, we believe in the Second Amendment, but we also believe in common sense gun violence laws.

And then when it came time to draw a sharp contrast with their opponents, Tim Walz said, these guys are phonies.

Donald Trump is not fighting for you or your family. He never sat at that kitchen table like the one I grew up at, wondering how we were going to pay the bills. He sat at his country club in Mar-a-Lago, wondering how he can cut taxes for his rich friends.

He said it’s actually people like me and Kamala Harris who come from humble origins and showed what is possible in America when you hail from a working class background, and you seize opportunities that were available to you.

Thank you, Philadelphia. Thank you, Vice President. God bless America.

So when it comes to this question of Walz’s dual identities and dual appeals, what did we learn on day one of this new Democratic ticket, do you think?

I think the campaign is trying to convey that these two facets of Tim Walz’s life are not mutually exclusive, that they don’t need to be in tension. They don’t cancel each other out. They’re both part of Tim Walz’s story. And I think that’s how they’re going to present him from now until Election Day.

Ernesto, thank you very much. We appreciate it.

It’s my pleasure, Michael.

Here’s what else you need to know today. On Tuesday, Hamas said that Yahya Sinwar, one of the masterminds behind the deadly October 7 attacks on Israel, had consolidated his power over the entire organization. Until now, Sinwar had held the title of Hamas’s leader in Gaza. But with the assassination of Hamas’s top political leader by Israel last week, Hamas said that Sinwar would take on that title as well. Sinwar remains a major target of Israel and is believed to have been hiding in tunnels underneath Gaza since October 7.

And the US Department of Justice has charged a Pakistani man with ties to Iran with trying to hire a hitman to assassinate political figures in the United States. The man recently traveled to the US and was arrested in New York last month. American authorities believe that his potential targets likely included former President Trump.

Today’s episode was produced by Alex Stern, Eric Krupke, and Olivia Natt. It was edited by Lisa Chow and Patricia Willens, contains original music by Pat McCusker and Marion Lozano, and was engineered by Alyssa Moxley. Our theme music is by Jim Brunberg and Ben Landsverk of Wonderly. Special thanks to Nick Pittman and Minnesota Public Radio.

That’s it for “The Daily.” I’m Michael Barbaro. See you tomorrow.

• Apple Podcasts
• Google Podcasts

Hosted by Michael Barbaro

Featuring Ernesto Londoño

Produced by Alex Stern Eric Krupke and Olivia Natt

Edited by Lisa Chow and Patricia Willens

Original music by Marion Lozano and Pat McCusker

Engineered by Alyssa Moxley

Listen and follow The Daily Apple Podcasts | Spotify | Amazon Music | YouTube

Earlier this summer, few Democrats could have identified Gov. Tim Walz of Minnesota.

But, in a matter of weeks, Mr. Walz has garnered an enthusiastic following in his party, particularly among the liberals who cheer on his progressive policies. On Tuesday, Vice President Kamala Harris named him as her running mate. Ernesto Londoño, who reports for The Times from Minnesota, walks us through Mr. Walz’s career, politics and sudden stardom.

On today’s episode

Ernesto Londoño , a reporter for The Times based in Minnesota, covering news in the Midwest.

Background reading

Who is Tim Walz , Kamala Harris’s running mate?

Mr. Walz has faced criticism for his response to the George Floyd protests.

There are a lot of ways to listen to The Daily. Here’s how.

We aim to make transcripts available the next workday after an episode’s publication. You can find them at the top of the page.

The Daily is made by Rachel Quester, Lynsea Garrison, Clare Toeniskoetter, Paige Cowett, Michael Simon Johnson, Brad Fisher, Chris Wood, Jessica Cheung, Stella Tan, Alexandra Leigh Young, Lisa Chow, Eric Krupke, Marc Georges, Luke Vander Ploeg, M.J. Davis Lin, Dan Powell, Sydney Harper, Michael Benoist, Liz O. Baylen, Asthaa Chaturvedi, Rachelle Bonja, Diana Nguyen, Marion Lozano, Corey Schreppel, Rob Szypko, Elisheba Ittoop, Mooj Zadie, Patricia Willens, Rowan Niemisto, Jody Becker, Rikki Novetsky, Nina Feldman, Will Reid, Carlos Prieto, Ben Calhoun, Susan Lee, Lexie Diao, Mary Wilson, Alex Stern, Sophia Lanman, Shannon Lin, Diane Wong, Devon Taylor, Alyssa Moxley, Olivia Natt, Daniel Ramirez and Brendan Klinkenberg.

Our theme music is by Jim Brunberg and Ben Landsverk of Wonderly. Special thanks to Sam Dolnick, Paula Szuchman, Lisa Tobin, Larissa Anderson, Julia Simon, Sofia Milan, Mahima Chablani, Elizabeth Davis-Moorer, Jeffrey Miranda, Maddy Masiello, Isabella Anderson, Nina Lassam and Nick Pitman.

An earlier version of this episode misstated the subject that Walz’s wife taught. She taught English, not Social Studies.

How we handle corrections

Ernesto Londoño is a Times reporter based in Minnesota, covering news in the Midwest and drug use and counternarcotics policy. More about Ernesto Londoño

Advertisement