Scholarlink

<p>Multifamily housing serves as a crucial residential option for millions of households across the United States, with maintenance being an essential component. However, there are limited studies examining whether maintenance factors are reflected in multifamily rent prices. To address this research gap, this study employs an integrated method combining computer vision, machine learning, and hedonic modeling to investigate the determinants of multifamily rent prices. Specifically, we utilize computer vision techniques and Google Street View images to evaluate outdoor maintenance levels. Additionally, we use violation severity index data from a recent micro-level multifamily housing survey to assess indoor maintenance levels. By implementing a multilevel linear model and machine learning techniques, specifically random forest, we examine the influence of both indoor and outdoor maintenance on multifamily rents. Our findings reveal that both indoor and outdoor maintenance significantly impact rental prices. These insights have important implications for property owners, renters, urban planners, and policymakers focused on housing issues.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Assessing the impact of maintenance condition on multifamily rents: an integrated approach of machine learning and hedonic modelling

  • 期刊论文

  • 发表日期：

    2025年4月9日

查看全文
  • Qiong Peng,
  • Grace Zhao,
  • Xinyue Ye

摘要

Multifamily housing serves as a crucial residential option for millions of households across the United States, with maintenance being an essential component. However, there are limited studies examining whether maintenance factors are reflected in multifamily rent prices. To address this research gap, this study employs an integrated method combining computer vision, machine learning, and hedonic modeling to investigate the determinants of multifamily rent prices. Specifically, we utilize computer vision techniques and Google Street View images to evaluate outdoor maintenance levels. Additionally, we use violation severity index data from a recent micro-level multifamily housing survey to assess indoor maintenance levels. By implementing a multilevel linear model and machine learning techniques, specifically random forest, we examine the influence of both indoor and outdoor maintenance on multifamily rents. Our findings reveal that both indoor and outdoor maintenance significantly impact rental prices. These insights have important implications for property owners, renters, urban planners, and policymakers focused on housing issues.