Proceedings of the 5th Management Science Informatization and Economic Innovation Development Conference, MSIEID 2023, December 8–10, 2023, Guangzhou, China

Research Article

Research on Renting Price Prediction Based on Machine Learning

Download124 downloads
  • @INPROCEEDINGS{10.4108/eai.8-12-2023.2344718,
        author={Shixuan  Cao and Weize  Liao and Jianrong  Huang},
        title={Research on Renting Price Prediction Based on Machine Learning},
        proceedings={Proceedings of the 5th Management Science Informatization and Economic Innovation Development Conference, MSIEID 2023, December 8--10, 2023, Guangzhou, China},
        publisher={EAI},
        proceedings_a={MSIEID},
        year={2024},
        month={4},
        keywords={rent; knn; xgboost; random forests; forecasting},
        doi={10.4108/eai.8-12-2023.2344718}
    }
    
  • Shixuan Cao
    Weize Liao
    Jianrong Huang
    Year: 2024
    Research on Renting Price Prediction Based on Machine Learning
    MSIEID
    EAI
    DOI: 10.4108/eai.8-12-2023.2344718
Shixuan Cao1, Weize Liao2,*, Jianrong Huang2
  • 1: United International College of Beijing Normal University and Hong Kong Baptist University
  • 2: Wuzhou University
*Contact email: 1375480613@qq.com

Abstract

This study uses housing data from the Beijing region retrieved from the rental portal website, Fang Tian Xia, as the research subject. The objective is to predict rental prices of various types of housing, approaching it as a regression problem in rental price prediction. Initially, an approximately 140,000-entry dataset was constructed by collecting housing data using a web crawler. Subsequently, three machine learning models—KNN, Random Forest, and XGBoost—were separately trained using the dataset. Based on evaluation metrics, the most effective model was selected, with results indicating that the Random Forest model demonstrated optimal performance. Finally, the most effective model was used to predict rental prices for various types of housing.