摘要
随着国家对二手车市场的进一步开放和"互联网+"的大力推广,C2B模式下的二手车拍卖网站快速发展。二手车市场被认为是汽车产业链上的最后一片蓝海。近年来,很多投资纷纷入驻二手车行业。笔者根据车系、车况等级、车龄、行驶里程、新车指导价、排放标准、过户情况和拍卖人数等特征,构建了基于XGBoost算法的二手车拍卖价格预测模型,分析了各特征对拍卖价格的影响。
With the further opening of the second-hand car market and the vigorous promotion of "Internet +",the secondhand car auction website under the C2 B mode has developed rapidly.The used car market is considered to be the last blue sea in the automotive industry chain.In recent years,many investments have entered the second-hand car industry.According to the characteristics of car system,vehicle condition grade,vehicle age,driving mileage,guidance price of new car,emission standard,transfer situation and auction number,the author constructs a prediction model of used car auction price based on XGBoost algorithm,and analyses the influence of each feature on auction price.
引文
[1]中国拍卖行业协会,商务部流通业发展司.中国拍卖行业发展报告(2017)[EB/OL].(2018-04-18)[2019-03-25].http://www.caa123.org.cn/frontnc06News Content Action.do?method=previewContent&ID=13914.
[2]中国拍卖行业协会.中国机动车拍卖市场统计年报[EB/OL].(2018-10-16)[2019-03-25].http://wemedia.ifeng.com/82377164/wemedia.shtml.
[3]Chen T,Guestrin C.XGBoost:A Scalable Tree Boosting System[C].//The 22nd ACM SIGKDD International Conference,2016.