电商平台用户再购物行为的预测研究  

Research on Prediction of Re-shopping Behavior of E-commerce Customers

作　　者：吕泽宇 李纪旋 陈如剑 陈东明[1] LV Ze-yu;LI Ji-xuan;CHEN Ru-Jian;CHEN Dong-ming(Software College,Northeastern University,Shenyang 110167,China)

机构地区：[1]东北大学软件学院,沈阳110167

出　　处：《计算机科学》2020年第S01期424-428,共5页Computer Science

基　　金：国家级大学生创新创业训练计划资助项目(201910145222);中央高校基本科研业务专项资金(N182410001)。

摘　　要：电商平台上用户的购物行为研究对于电商企业来说具有重要的商业应用价值。文中针对购物者在同一电商平台上的再次消费行为的预测问题进行了研究。首先,针对用户与商家的行为和交易记录,基于特征工程方法设计了多种不同的行为预测特征,基于可视化等方法对比分析了预测特征的重要性和特点,进行了属性筛选;然后,基于提出的预测特征设计使用了多种不同算法训练预测模型。实验研究表明,多lightGBM模型的融合方法能够达到很高的再购物行为预测准确度,其AUC值能够达到0.7018,同时,基于这种方法实现的预测器只需要少数特征就能对预测结果产生很好的贡献。研究的数据来源是开源的真实大数据,研究成果具有应用和学术双重价值。The study of customers’shopping behavior is a trending research topic and has great commercial value for e-commerce companies.This paper studies the prediction of customer’s re-shopping behavior on the same e-commerce platform.Through the analysis of shopping related actions of customers and transaction records between customers and merchants,a variety of different behavior features are designed based on feature engineering principles,and the importance and characteristics of the prediction features are analyzed by using visualization approaches.Then,based on the proposed predictive features,a variety of different algorithms are used to train the prediction models.Experimental research shows that the multi-lightGBM model ensemble method can achieve high prediction accuracy,and the AUC value can reach 0.7018.Meanwhile,the predictor only needs a few features to obtain very good prediction results.The experimental data set studied in this paper is an open source big data collected in real environment,and the research conclusions have both application and academic value.

关 键 词：再次购物行为预测 特征工程 特征可视化 融合模型 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]