基于机器学习的房价预测研究

House Price Prediction Based on Machine Learning

摘要: 房地产行业是我国国民经济的重要组成部分，关乎国计民生，而房价的走势直接影响到社会的金融稳定和整体宏观社会的长期发展，因此对房价进行预测研究对个人消费者、房地产开发商以及国家宏观调控部门都至关重要。本文基于Kaggle在线平台上2020年5月至2021年5月美国King County的房屋销售价格以及房屋的基本信息数据，分别利用支持向量机和XGBoost模型对房屋价格进行预测，采用平均绝对误差、均方根误差和拟合优度作为评价标准将各个预测模型对房价的预测效果进行评价与比较，得出结论：XGBoost模型拟合和预测的效果最好。整体而言，本研究为房价预测提供了科学的模型和方法，为房屋出售者和房屋购买者提供科学的参考依据。

Abstract: The real estate industry is an important component of China’s national economy, affecting livelihoods and national economic planning. Trends in housing prices directly impact financial stability and overall macroeconomic development. Therefore, researching and predicting housing prices are crucial for individual consumers, real estate developers, and national macroeconomic regulators. This study is based on housing sales data and basic property information from King County, USA, collected from May 2020 to May 2021 via the Kaggle platform. Support Vector Machine (SVM) and XGBoost models were employed to predict housing prices. Evaluation criteria including Mean Absolute Error, Root Mean Square Error, and coefficient of determination were used to assess and compare the predictive performance of these models. The conclusion drawn was that the XGBoost model demonstrated the best fitting and predictive performance. Overall, this research provides a scientific approach to housing price prediction, offering valuable insights for both sellers and buyers in the housing market.