Predictive Models for United States House Prices

Hongyi Yang

2024

Abstract

House prices are a crucial indicator affecting citizens’ lives, directly impacting individuals’ and families’ financial situations, as well as the stability and development of entire communities. Therefore, it is imperative to conduct in-depth research on the societal impact of house price prediction models, exploring their effects on housing markets, economic development, social welfare, and potential challenges and issues. This study addresses the issue of accurate house price prediction by conducting extensive analyses on four ensemble learning models: Random Forest, XGBoost, AdaBoost, and Stacking. The selected metrics for assessing model performance in this experiment include RMSE, R-squared, Explained Variance Score, and MAPE. The results demonstrate that the Random Forest model excels across multiple evaluation metrics, outperforming other models with the lowest RMSE and MAPE values. XGBoost shows strong competitiveness, providing accurate predictions and effectively capturing nonlinear relationships in the data, albeit slightly inferior to Random Forest. AdaBoost and Stacking exhibit moderate performance, possibly limited by their ability to handle complex relationships and noisy data.

Paper Citation

in Harvard Style

Yang H. (2024). Predictive Models for United States House Prices. In Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA; ISBN 978-989-758-722-1, SciTePress, pages 38-45. DOI: 10.5220/0012990800004601

in Bibtex Style

@conference{iampa24,
author={Hongyi Yang},
title={Predictive Models for United States House Prices},
booktitle={Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA},
year={2024},
pages={38-45},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012990800004601},
isbn={978-989-758-722-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA
TI - Predictive Models for United States House Prices
SN - 978-989-758-722-1
AU - Yang H.
PY - 2024
SP - 38
EP - 45
DO - 10.5220/0012990800004601
PB - SciTePress