查询结果:   谢勇,项薇,季孟忠,彭俊,黄益槐.基于Xgboost和LightGBM算法预测住房月租金的应用分析[J].计算机应用与软件,2019,36(9):151 - 155,191.
中文标题
基于Xgboost和LightGBM算法预测住房月租金的应用分析
发表栏目
应用技术与研究
摘要点击数
50
英文标题
AN APPLICATION AND ANALYSIS OF FORECAST HOUSING RENTAL BASED ON XGBOOST AND LIGHTGBM ALGORITHMS
作 者
谢勇 项薇 季孟忠 彭俊 黄益槐 Xie Yong Xiang Wei Ji Mengzhong Peng Jun Huang Yihuai
作者单位
宁波大学机械工程与力学学院 浙江 宁波 315211     
英文单位
Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, Zhejiang, China     
关键词
住房租金预测 Xgboost LightGBM
Keywords
Housing rental forecast Xgboost LightGBM
基金项目
作者资料
谢勇,硕士生,主研领域:工业工程。项薇,教授。季孟忠,硕士生。彭俊,硕士生。黄益槐,硕士生。 。
文章摘要
结合收集的住房月租金数据,通过合理处理异常缺失数据和设置多个数据集的预处理后,分别应用GBDT(Gradient Boosting Decision Tree)、Xgboost(eXtreme Gradient Boosting)和LightGBM三种机器学习模型对住房月租金进行预测。通过比较分析在不同数据集训练下的预测结果,发现Xgboost和LightGBM模型优于传统GBDT模型。同时发现影响住房月租金的关键因素主要包括房屋面积、小区所在商圈位置、房屋距离地铁的距离、房屋所在建筑的总楼层数和小区房屋出租数量等。预测模型及分析结果对住房租赁市场中住房租金价格的预测具有一定的参考价值。
Abstract
Combined with the collected monthly rent data, the abnormal missing data and multiple data sets were pre-processed reasonably, and three machine learning models, GBDT, Xgboost and LightGBM, were applied to predict the monthly rent of housing respectively. By comparing and analyzing the prediction results under different data sets training, it was found that Xgboost and LightGBM models were superior to traditional GBDT models. It was found that the key factors affecting the monthly rent of housing mainly included the area of housing, the location of business district, the distance between housing and subway, the total floor number of buildings and the number of rental houses. The forecasting model and analysis results have a certain reference value for the forecasting of housing rent price in the housing rental market.
下载PDF全文   

根据该篇关键词查找到本刊已发表相关论文供参考
序号
文  章  标  题
作者1
发表栏目
页码
摘要
1
基于Xgboost和LightGBM算法预测住房月租金的应用分析
谢勇
应用技术与研究
2019
9
151
[摘要]
2
基于机器学习的贫困生分类预测研究
陆桂明
信息技术交流
2019
1
316
[摘要]