基于机器学习的二手房价格预测研究

——以太原为例

打开文本图片集

中图分类号：TP391；F127 文献标识码：A 文章编号：2096-4706（2026）05-0046-05

Research on Second-hand House Price Prediction Based on Machine Learning -Taking Taiyuan as an Example

ZHU Lili，LI Yansong （Shanxi Institute ofEnergy，Jinzhong O3o6oo， China）

Abstract： Second-hand housing transaction price evaluation has important reference value and provides abasis for the decision-makingof govemments，house buyers，selersandreal estateagencies.This paper takessecond-handhouse prices in TaiyuancityShanxiProvinceastheresearchobject，constructspredictionmodelsandselects theoptimalschemebyomparing modeleffects.Firstly，Webcrawlertechnologyisusedtoobtainsecond-handhousingdataofTaiyuanfromLianjiawebsite， and8394datarecords including 63 mostrepresentativecharacteristic variablesarefinallobtainedforhousepriceprediction. Secondly，thematplotliblbraryofytonisusedtoconductvisualresearchfromthreeaspects：locationcharacteisticsbuilding characteristicsandtransactioncharacteristics，andthe influencerelationship between houseprices andvarious variables is initiallydetermined.Falyinordertoselectteoptialmodeltopredicttechangesofsecond-handhousepricesinTaiuan， the CARTDecision Tree modeland the XGBoost model are constructed respectively.The modelcomparison results show that the XGBoost model has high accuracy and is more suitable for second-hand house price prediction.

Keywords： second-hand house price; CART Decision Tree model; Machine Learning; XGBoost model

0 引言

2023年底，山西省太原市房产成交减免税费的利好政策覆盖到二手房市场[1-3]。（剩余6123字）