用集成学习精准预测房价，提升买卖双方决策效率。
Using ensemble methods of machine learning to predict real estate prices
- 采用梯度提升、随机森林等集成模型进行房价预测。
- 梯度提升回归器表现最优，R²接近0.9，误差低于15%。
- 适合房地产投资与智能估价系统开发者参考。
近年来，机器学习技术已成为提升预测精度和决策能力的强大工具，并逐步渗透至房地产领域。准确预测房产价值对买卖双方至关重要，有助于合理设定价格预期并规避财务风险。本文评估了多种集成机器学习方法在房价预测中的表现。结果表明，梯度提升回归器（Gradient Boosting Regressor）精度最高，其他如极端随机树（Extra Trees Regressor）、历史梯度提升（Hist Gradient Boosting Regressor）和随机森林（Random Forest Regressor）也表现良好。通过决定系数（R²）、均方根误差（RMSE）和平均绝对误差（MAE）等指标验证，模型整体预测效果显著。研究为未来工作提供了方向：包括数据预处理中异常值检测与实际应用落地。
原文摘要 · Abstract (English)
In recent years, machine learning (ML) techniques have become a powerful tool for improving the accuracy of predictions and decision-making. Machine learning technologies have begun to penetrate all areas, including the real estate sector. Correct forecasting of real estate value plays an important role in the buyer-seller chain, because it ensures reasonableness of price expectations based on the offers available in the market and helps to avoid financial risks for both parties of the transaction. Accurate forecasting is also important for real estate investors to make an informed decision on a specific property. This study helps to gain a deeper understanding of how effective and accurate ensemble machine learning methods are in predicting real estate values. The results obtained in the work are quite accurate, as can be seen from the coefficient of determination (R^2), root mean square error (RMSE) and mean absolute error (MAE) calculated for each model. The Gradient Boosting Regressor model provides the highest accuracy, the Extra Trees Regressor, Hist Gradient Boosting Regressor and Random Forest Regressor models give good results. In general, ensemble machine learning techniques can be effectively used to solve real estate valuation. This work forms ideas for future research, which consist in the preliminary processing of the data set by searching and extracting anomalous values, as well as the practical implementation of the obtained results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。