Sequential Recommendation Model for Next Purchase Prediction

TL;DR

This paper presents a sequential recommendation system that leverages transaction order data and deep learning to improve next purchase prediction, demonstrating competitive accuracy on a large credit card dataset.

Contribution

It introduces a novel sequential recommendation approach combining autoencoders and GRUs, with practical implications for real-time digital marketing applications.

Findings

Achieved MAP@1 of 47% on test data.

Utilized over 2.7 million transactions for model training.

Discussed integration into scalable digital platforms.

Abstract

Timeliness and contextual accuracy of recommendations are increasingly important when delivering contemporary digital marketing experiences. Conventional recommender systems (RS) suggest relevant but time-invariant items to users by accounting for their past purchases. These recommendations only map to customers' general preferences rather than a customer's specific needs immediately preceding a purchase. In contrast, RSs that consider the order of transactions, purchases, or experiences to measure evolving preferences can offer more salient and effective recommendations to customers: Sequential RSs not only benefit from a better behavioral understanding of a user's current needs but also better predictive power. In this paper, we demonstrate and rank the effectiveness of a sequential recommendation system by utilizing a production dataset of over 2.7 million credit card transactions for 46K cardholders. The method first employs an autoencoder on raw transaction data and submits observed transaction encodings to a GRU-based sequential model. The sequential model produces a MAP@1 metric of 47% on the out-of-sample test set, in line with existing research. We also discuss implications for embedding real-time predictions using the sequential RS into Nexus, a scalable, low-latency, event-based digital experience architecture.