当前位置: X-MOL 学术Journal of Property Research › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Predicting owner-occupied housing values using machine learning: an empirical investigation of California census tracts data
Journal of Property Research Pub Date : 2021-04-13 , DOI: 10.1080/09599916.2021.1890187
Prodosh E. Simlai 1
Affiliation  

ABSTRACT

In this paper, we introduce machine-learning (ML) methods to evaluate one of the key concepts of real estate analysis – the prediction of housing prices in the presence of a large number of covariates. We use several supervised ML tools that are based on regularisation methods – notably Ridge, LASSO, and Elastic Net regressions – and discuss their relative performance in comparison to conventional OLS-based methods. Our empirical results show that the supervised ML methods provide a comprehensive description of the determinants of owner-occupied housing values in the census tracts of California. We find that, compared to the familiar worlds of OLS and WLS, the Ridge, LASSO, and Elastic Net regressions provide relatively better out-of-sample predictions. Among the benefits of shrinkage-based ML methods are their ability to resolve such issues as variable selection and overfitting.



中文翻译:

使用机器学习预测自住房屋价值:加利福尼亚人口普查数据的实证调查

摘要

在本文中,我们引入了机器学习 (ML) 方法来评估房地产分析的关键概念之一——在存在大量协变量的情况下预测房价。我们使用了几种基于正则化方法的监督 ML 工具——特别是 Ridge、LASSO 和 Elastic Net 回归——并讨论了它们与基于 OLS 的传统方法相比的相对性能。我们的实证结果表明,受监督的 ML 方法全面描述了加利福尼亚州人口普查区自住住房价值的决定因素。我们发现,与熟悉的 OLS 和 WLS 世界相比,Ridge、LASSO 和 Elastic Net 回归提供了相对更好的样本外预测。

更新日期:2021-04-13
down
wechat
bug