Sequence-aware item recommendations for multiply repeated user-item interactions

TL;DR

This paper introduces a sequence-aware recommender system inspired by NLP techniques, which models user interaction sequences to improve prediction accuracy and increase sales in retail environments.

Contribution

It presents a novel sequence-based recommendation approach that captures temporal user behavior, outperforming traditional methods in accuracy and sales impact.

Findings

Achieved 5% increase in total sales

Over 50% increase in individual customer expenditure

Improved prediction accuracy for repeated user-item interactions

Abstract

Recommender systems are one of the most successful applications of machine learning and data science. They are successful in a wide variety of application domains, including e-commerce, media streaming content, email marketing, and virtually every industry where personalisation facilitates better user experience or boosts sales and customer engagement. The main goal of these systems is to analyse past user behaviour to predict which items are of most interest to users. They are typically built with the use of matrix-completion techniques such as collaborative filtering or matrix factorisation. However, although these approaches have achieved tremendous success in numerous real-world applications, their effectiveness is still limited when users might interact multiple times with the same items, or when user preferences change over time. We were inspired by the approach that Natural Language Processing techniques take to compress, process, and analyse sequences of text. We designed a recommender system that induces the temporal dimension in the task of item recommendation and considers sequences of item interactions for each user in order to make recommendations. This method is empirically shown to give highly accurate predictions of user-items interactions for all users in a retail environment, without explicit feedback, besides increasing total sales by 5% and individual customer expenditure by over 50% in an A/B live test.