Predicting House Prices Using Machine Learning

Authors

Pejal Rath, Southern Methodist UniversityFollow
Robert Slater, SMUFollow

Abstract

This study explores the use of Machine Learning methods to predict housing prices, a problem of significant interest in real estate economics, and data science. Traditional hedonic pricing models have long been used to evaluate the impact of housing attributes on property values, but they often lack the flexibility to capture nonlinear relationships and complex feature interactions. Recent advancements in regression based and Machine Learning approaches provide promising alternatives that may improve prediction of accuracy and market insights. This research will investigate how models such as linear regression, random forest, and gradient boosting can be applied to publicly available housing datasets. The study will contribute to both academic understanding and practical applications by comparing the performance of traditional and Machine Learning models.

Recommended Citation

Rath, Pejal and Slater, Robert (2025) "Predicting House Prices Using Machine Learning," SMU Data Science Review: Vol. 9: No. 3, Article 12.
Available at: https://scholar.smu.edu/datasciencereview/vol9/iss3/12