Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26–28, 2023, Nanjing, China

Research Article

Machine Learning based Comparative Study on House Price Prediction Task

Download197 downloads
  • @INPROCEEDINGS{10.4108/eai.26-5-2023.2334435,
        author={Ruodong  Hu},
        title={Machine Learning based Comparative Study on House Price Prediction Task},
        proceedings={Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26--28, 2023, Nanjing, China},
        publisher={EAI},
        proceedings_a={MSEA},
        year={2023},
        month={7},
        keywords={house price prediction model regression},
        doi={10.4108/eai.26-5-2023.2334435}
    }
    
  • Ruodong Hu
    Year: 2023
    Machine Learning based Comparative Study on House Price Prediction Task
    MSEA
    EAI
    DOI: 10.4108/eai.26-5-2023.2334435
Ruodong Hu1,*
  • 1: University of Macau
*Contact email: dc02755@um.edu.mo

Abstract

Because it enables buyers and sellers to make informed decisions about purchasing and selling real estate, house price prediction is important. Additionally, it aids banks and other financial organizations in determining the worth of a property when taking into account a mortgage or loan application. It also aids real estate agents and brokers in pricing homes appropriately. The use of machine learning and neural networks to anticipate home prices has been extensively studied. In one publication, an approach is put out for predicting housing prices with real inputs utilizing a variety of regression techniques. In order to examine the precision of the four models—linear regression, random forest regressor, XGBoost regressor, and support vector machine regressor—in predicting Boston home prices, no study has been done. The importance of this study is to evaluate how well these four models forecast Boston home values.