Modeling and Analyzing the Influence of Non-Item Pages on Sequential Next-Item Prediction

TL;DR

This paper introduces a method to incorporate non-item pages into sequential recommendation models, demonstrating that their inclusion improves next-item prediction accuracy across various models and datasets.

Contribution

It proposes a general framework for integrating non-item pages into sequential recommendation models and evaluates their impact on prediction performance.

Findings

Non-item pages significantly influence user interactions.

Inclusion of non-item pages improves model accuracy.

Models effectively handle noisy data with non-item pages.

Abstract

Analyzing sequences of interactions between users and items, sequential recommendation models can learn user intent and make predictions about the next item. Next to item interactions, most systems also have interactions with what we call non-item pages: these pages are not related to specific items but still can provide insights into the user's interests, as, for example, navigation pages. We therefore propose a general way to include these non-item pages in sequential recommendation models to enhance next-item prediction. First, we demonstrate the influence of non-item pages on following interactions using the hypotheses testing framework HypTrails and propose methods for representing non-item pages in sequential recommendation models. Subsequently, we adapt popular sequential recommender models to integrate non-item pages and investigate their performance with different item representation strategies as well as their ability to handle noisy data. To show the general capabilities of the models to integrate non-item pages, we create a synthetic dataset for a controlled setting and then evaluate the improvements from including non-item pages on two real-world datasets. Our results show that non-item pages are a valuable source of information, and incorporating them in sequential recommendation models increases the performance of next-item prediction across all analyzed model architectures.