摘要
近年来,网络零售保持高速增长,网站中富含大量的用户行为数据。电商平台中的用户对商品的操作行为可以体现用户偏好,如何利用用户行为挖掘用户偏好已经成为学术界和工业界的关注焦点,并已经取得了众多研究成果。然而,目前用户操作行为预测方法研究通常只针对用户某一类操作行为进行分析,无法完备反映用户行为的整体特征。因此,提出一种基于深度森林的用户购买行为预测模型,通过构建用户行为特征工程建立整体用户行为特征模型;基于此,提出基于深度森林的用户购买行为预测方法,实现高效的行为预测训练效果。该方法的训练时间为43s,F1值为9.73%,相对其他模型取得了更好的效果。实验结果表明,该模型在降低时间开销的同时,提高了预测准确率。
In recent years,online retail kept growing at a high speed.There exist redundant user behavior data in website.User’s behavior can embody user’ s preference in the e-commerce platform.How to utilize user behavior to mine user preferences has become the focus of attention in academia and industry,and has formed a number of research results.The prediction methods of user behavior only aims at a certain type of user behavior, which is not able to reflect the overall characteristics of user behavior.Therefore,this paper proposed deep forest based prediction model of purchase behavior.By constructing feature engineering of user behavior ,a whole user behavior feature model was built.In order to achieve efficient training,a deep forest based prediction method of purchase behavior was put forward to implement the behavior recognition training effect.The training time of this method is 43 s,and the F1 value is 9.73%.Compared with other models,this method has achieved good results in both indexes.Finally,the experiments show that the model has an ability to reduce the time overhead and improve the prediction accuracy.
作者
葛绍林
叶剑
何明祥
GE Shao-lin;YE Jian;HE Ming-xiang(College of Computer Science and Engineering,Shandong University ofScience and Technology,Qingdao,Shandong 266590,China;Research Center for Ubiquitous Computing Systems,Institute of ComputingTechnology,Chinese Academy of Sciences,Beijing 100190,China;The Beijing Key Laboratory of Mobile Computing and Pervasive Device,Beijing 100190,China)
出处
《计算机科学》
CSCD
北大核心
2019年第9期190-194,共5页
Computer Science
基金
国家重点研发计划项目(2016YFB1001100)
国家自然科学青年基金课题(61401040)资助
关键词
用户行为特征
深度森林
特征工程
购买行为预测
Characteristics of user behavior
Deep forest
Feature engineering
Prediction of purchase behavior
