Machine-Learning-Based Approach for Anonymous Online Customer Purchase Intentions Using Clickstream Data

Abstract

Since online shopping has become an important way for consumers to make purchases, consumers have signed up to e-commerce platforms to shop online. However, retailers are beginning to realise the critical role of predicting anonymous consumer purchase intent to improve purchase conversion rates and store profitability. Therefore, this study aims to investigate the prediction of anonymous consumer purchase intent. This research presents a machine learning model (MBT-POP) for predicting customer purchase behaviour based on multi-behavioural trendiness (MBT) and product popularity (POP) using 33,339,730 clicks generated from 445,336 sessions of real e-commerce customers. The results show that the MBT-POP model can effectively predict the purchase behaviour of anonymous customers (F1 = 0.9031), and it achieves the best prediction result with a sliding window of 2 days. Compared to existing studies, the MBT-POP model not only improves the model performance, but also compresses the number of days required for accurate prediction. The present research has argued that product trendiness and popularity can significantly improve the predictive performance of the customer purchase behaviour model and can play an important role in predicting the purchase behaviour of anonymous customers.

Optimizing Decision-Making Through Customer-Centric Market Basket Analysis

“…Market association rules, a technique within the field of machine learning, are employed to identify the presence of co-occurring items within transaction datasets. This method uses metrics, specifically support and confidence, to assess the strength of these associations [24]. The acquisition of an item's support value is computed using the formula provided in Eq.…”

Performance of aging consumers in an e-commerce product choice task: The role of working memory and decision strategies

“…The underlying assumption that users of e-commerce systems make choices that are optimal or, at least, in some broad sense beneficial for themselves, is the basis of research on recommendation systems. Much research has been done with the goal of predicting purchase intent of consumers based on logs of their sessions on e-commerce platforms [26][27][28][29] and behavioral data, including mouse movements and keyboard clicks [30]. More advanced approaches also use eye-tracking data [31].…”