Premium
Brand purchase prediction based on time‐evolving user behaviors in e‐commerce
Author(s) -
Dong Yunqi,
Jiang Wenjun
Publication year - 2018
Publication title -
concurrency and computation: practice and experience
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.309
H-Index - 67
eISSN - 1532-0634
pISSN - 1532-0626
DOI - 10.1002/cpe.4882
Subject(s) - computer science , feature (linguistics) , promotion (chess) , construct (python library) , key (lock) , focus (optics) , e commerce , predictive modelling , function (biology) , logistic regression , machine learning , world wide web , computer security , philosophy , linguistics , physics , optics , evolutionary biology , politics , political science , law , biology , programming language
Summary Purchase prediction is a key function in the e‐commerce recommendation system. Existing works usually focus on item‐level purchase prediction, which faces two issues of high cost and low accuracy. In this paper, we study brand purchase prediction by exploring behaviors, which may lead to brand purchases. We make three progresses. (1) We analyze a real world e‐commerce data from multiple angles. Focusing on users' brand purchases, we find behaviors' evolution with time and behaviors' interaction. (2) For different behaviors, we extract different time‐evolving features that can serve as indicators of users' brand purchase. (3) We use a logistic regression‐based model by adjusting the parameters of time‐evolving feature and others in two different scenarios (the promotion purchase prediction and the daily purchase prediction) to construct two experiments. The experiment results show that the model using three types features performs the best in both scenarios, and the time‐evolving feature plays the most important role among them. (4) We distinguish the feature importance in different scenarios. Based on the importance, we find that users' purchases in the promotion scenario are likely to be impulsive, while purchases in the daily scenario are more likely to be influenced by users' activities.