An analyses of the effect of using contextual and loyalty features on early purchase prediction of shoppers in e-commerce domain

Abstract

Online sales have been growing rapidly in recent years. With the growing competition, online retailers have been keen to increase the effectiveness of their e-commerce platforms by providing a more personalised experience and increasing the ”conversion rate” (i.e. the proportion of visits ending in sales). The early identification of those customers who are likely to buy items could significantly improve the ”conversion rate”. In this paper, we present a novel framework of early purchase prediction in online sessions for registered and unregistered consumers as soon as they land on an e-commerce platform. Also, the paper provides extensive analysis of the performance of different data mining models using the proposed framework. Computational experiments on real-world datasets show that the proposed framework produces good results when appropriate session features are selected in the data mining model training stage, even when no products are browsed during the session. Contextual features without navigational data in the sessions can be used for early detection. When users arrive at the e-commerce platform, before any item interaction, we are able to predict which sessions will result in purchases early, with a high accuracy of 90.2 %. When we combine users’ past number of visits and purchase data, the performance has an even a higher accuracy of 95.6 %. The findings in this paper provide an understanding of context features and users’ loyalty related features that can help online shops’ marketing strategies as well as delivering a better user experience through personalised offers and discounts based on users’ early purchase predictions.