Towards Purchase Prediction: A Transaction-based Setting and A Graph-based Method Leveraging Price Information

Zongxi LI, Haoran XIE, Guandong XU, Qing LI, Mingming LENG, Chi ZHOU

Research output: Journal PublicationsJournal Article (refereed)peer-review

1 Citation (Scopus)

Abstract

Targeting at boosting business revenue, purchase prediction based on user behavior is crucial to e-commerce. However, it is not a well-explored topic due to a lack of relevant datasets. Specifically, no public dataset provides both price and discount information varying on time, which play an essential role in the user’s decision making. Besides, existing learn-to-rank methods cannot explicitly predict the purchase possibility for a specific user-item pair. In this paper, we propose a two-step graph-based model, where the graph model is applied in the first step to learn representations of both users and items over click-through data, and the second step is a classifier incorporating the price information of each transaction record. To evaluate the model performance, we propose a transaction-based framework focusing on the purchased items and their context clicks, which contain items that a user is interested in but fails to choose after comparison. Our experiments show that exploiting the price and discount information can significantly enhance prediction accuracy.
Original languageEnglish
Article number107824
JournalPattern Recognition
Volume113
Early online date22 Jan 2021
DOIs
Publication statusPublished - May 2021

Bibliographical note

The research described in this article has been supported by the Lam Woo Research Grant (LWI20011), Faculty Research Grant (102041), Direct Grant (101138) and the Research Seed Fund (102367) at Lingnan University, Hong Kong.

Keywords

  • Graph-based method
  • Purchase prediction
  • Transaction-level data
  • e-commerce

Fingerprint

Dive into the research topics of 'Towards Purchase Prediction: A Transaction-based Setting and A Graph-based Method Leveraging Price Information'. Together they form a unique fingerprint.

Cite this