How much is the view from the window worth? Machine learning-driven hedonic pricing model of the real estate market

Potrawa, Tomasz; Tetereva, Anastasija

doi:10.1016/j.jbusres.2022.01.027

Cited by 47 publications

(17 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li & Huang, 2020; N. Li et al, 2021; Potrawa & Tetereva, 2022; Xiao et al, 2019). Since each housing unit is unique with different features, the housing price is different.…”

Section: Methodsmentioning

confidence: 99%

The Impact of Recognized Features of Uncomfortable Houses on Auction Prices: A Chinese Cultural Perspective

Kuo,

Yuan,

Gao

et al. 2023

Sage Open

View full text Add to dashboard Cite

This study examines the influence of negative Feng-shui features on the prices of foreclosures (the houses subject to court-enforced auction) in Taiwan using the Google Street View function. The research objectives are threefold. Firstly, the study aims to compare whether foreclosed houses with negative Feng-shui features have longer auction times and higher discount rates compared to those without such features. Secondly, it seeks to explore the impact of negative Feng-shui features on investors in the foreclosed house market. Lastly, the study aims to assess the varying degrees of influence of different negative Feng-shui features on foreclosure prices. The findings of this study indicate that in the metropolitan area of Taiwan, foreclosures with more negative Feng-shui features tend to have longer auction times and higher discount rates compared to those without such features. Negative Feng-shui features may cause delays in investor bidding. Among the 12 negative Feng-shui features analyzed, only the presence of “facing-temple” is found to have a negative effect on foreclosure prices. This suggests that foreclosures with the “facing-temple” feature tend to have lower prices and potentially higher discount rates. The other 11 negative Feng-shui features do not have significant effects on auction pricing. This study discovered that the “facing-temple” was a significant negative Feng-shui feature in foreclosures in Taiwan against the traditional perspective. And it provides investors’ concerns toward foreclosures and their tendency in prices of foreclosures in Taiwan.

show abstract

“…Li & Huang, 2020; N. Li et al, 2021; Potrawa & Tetereva, 2022; Xiao et al, 2019). Since each housing unit is unique with different features, the housing price is different.…”

Section: Methodsmentioning

confidence: 99%

The Impact of Recognized Features of Uncomfortable Houses on Auction Prices: A Chinese Cultural Perspective

Kuo,

Yuan,

Gao

et al. 2023

Sage Open

View full text Add to dashboard Cite

show abstract

“…Following the other papers which conducted topic modeling [ 20 , 56 , 77 ], we performed preprocessing before our text analysis using the re module [ 74 ]. The detailed process is as follows.…”

Section: Methodsmentioning

confidence: 99%

Online listing data and their interaction with market dynamics: evidence from Singapore during COVID-19

Lee

2023

J Big Data

View full text Add to dashboard Cite

With the emergence of Property Technology, online listing data have drawn increasing interest in the field of real estate–related big data research. Scraped from the online platforms for property search and marketing, these data reflect real-time information on housing supply and potential demand before actual transaction data are released. This paper analyzes the interactions between the keywords of online home listings and actual market dynamics. To do so, we link the listing data from the major online platform in Singapore with the universal transaction data of resale public housing. We consider the COVID-19 outbreak as a natural shock that brought a significant change to work modes and mobility and, in turn, consumer preference changes for home purchases. Using the Difference-in-Difference approach, we first find that housing units with a higher floor level and more rooms have experienced a significant increase in transaction prices while close proximity to public transportation and the central business district (CBD) led to a reduction in the price premium after COVID-19. Our text analysis results, using the natural language processing, suggest that the online listing keywords have consistently captured these trends and provide qualitative insights (e.g. view becoming increasingly popular) that could not be uncovered from the conventional database. Relevant keywords reveal trends earlier than transaction-based data, or at least in a timely manner. We demonstrate that big data analytics could effectively be applied to emerging social science research such as online listing research and provide useful information to forecast future market trends and household demand.

show abstract

“…it is able to explain variation in dwelling price and determine impact of specific attributes (location and structure) on house values. This method is widely tested and used in numerous papers such as Yazdani (2021), Potrawa and Donkers (2020), Chen et al (2020) and Limsombunchai (2004). As concluded from Yazdani, hedonic price regression is limited when it comes to uncovering non-linear relationships between housing price and characteristics.…”

Section: Literature Reviewmentioning

confidence: 99%

“…From the above literature analysis of the hedonic model, it is noticeable that hedonic model is lacking of the ability in dealing with non-linear relationship; it requires extensive human involvement in feature engineering, which will possibly cause biases and subjectivity causing the prediction to be inaccurate. Besides, the data needs to be homoscedastic, which means the variance of error should be similar at all levels of independent variable, and the residual of the model should not correlate with each other (Potrawa and Donkers, 2020). Therefore, ML and deep learning have the superiority of being more flexible as no assumptions or predefined functions are needed for them.…”

Section: Literature Reviewmentioning

confidence: 99%

Explainable housing price prediction with determinant analysis

Teoh

Yau

Ong

et al. 2022

IJHMA

View full text Add to dashboard Cite

Purpose This study aims to develop a regression-based machine learning model to predict housing price, determine and interpret factors that contribute to housing prices using different data sets available publicly. The significant determinants that affect housing prices will be first identified by using multinomial logistics regression (MLR) based on the level of relative importance. A comprehensive study is then conducted by using SHapley Additive exPlanations (SHAP) analysis to examine the features that cause the major changes in housing prices. Design/methodology/approach Predictive analytics is an effective way to deal with uncertainties in process modelling and improve decision-making for housing price prediction. The focus of this paper is two-fold; the authors first apply regression analysis to investigate how well the housing independent variables contribute to the housing price prediction. Two data sets are used for this study, namely, Ames Housing dataset and Melbourne Housing dataset. For both the data sets, random forest regression performs the best by achieving an average R2 of 86% for the Ames dataset and 85% for the Melbourne dataset, respectively. Second, multinomial logistic regression is adopted to investigate and identify the factor determinants of housing sales price. For the Ames dataset, the authors find that the top three most significant factor variables to determine the housing price is the general living area, basement size and age of remodelling. As for the Melbourne dataset, properties having more rooms/bathrooms, larger land size and closer distance to central business district (CBD) are higher priced. This is followed by a comprehensive analysis on how these determinants contribute to the predictability of the selected regression model by using explainable SHAP values. These prominent factors can be used to determine the optimal price range of a property which are useful for decision-making for both buyers and sellers. Findings By using the combination of MLR and SHAP analysis, it is noticeable that general living area, basement size and age of remodelling are the top three most important variables in determining the house’s price in the Ames dataset, while properties with more rooms/bathrooms, larger land area and closer proximity to the CBD or to the South of Melbourne are more expensive in the Melbourne dataset. These important factors can be used to estimate the best price range for a housing property for better decision-making. Research limitations/implications A limitation of this study is that the distribution of the housing prices is highly skewed. Although it is normal that the properties’ price is normally cluttered at the lower side and only a few houses are highly price. As mentioned before, MLR can effectively help in evaluating the likelihood ratio of each variable towards these categories. However, housing price is originally continuous, and there is a need to convert the price to categorical type. Nonetheless, the most effective method to categorize the data is still questionable. Originality/value The key point of this paper is the use of explainable machine learning approach to identify the prominent factors of housing price determination, which could be used to determine the optimal price range of a property which are useful for decision-making for both the buyers and sellers.

show abstract

How much is the view from the window worth? Machine learning-driven hedonic pricing model of the real estate market

Cited by 47 publications

References 70 publications

The Impact of Recognized Features of Uncomfortable Houses on Auction Prices: A Chinese Cultural Perspective

The Impact of Recognized Features of Uncomfortable Houses on Auction Prices: A Chinese Cultural Perspective

Online listing data and their interaction with market dynamics: evidence from Singapore during COVID-19

Explainable housing price prediction with determinant analysis

Contact Info

Product

Resources

About