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

2024-08-28

arXiv.org

AI Summary

This paper addresses the incomplete user behavior modeling in sequential recommendation caused by neglecting non-product pages (e.g., navigation pages). It is the first work to systematically validate their informational value and propose a general representation method alongside a scalable framework for integrating such pages into existing models. Methodologically, it combines HypTrails-based hypothesis testing, GRU/Transformer-based sequential modeling, multi-strategy item representation, synthetic data generation, and noise-robustness analysis. Evaluated on two real-world datasets, the approach achieves significant improvements in Recall@20 and MRR across diverse baseline models, demonstrating consistent gains. Key contributions are: (1) establishing the critical role of non-product pages in sequential recommendation; and (2) providing a lightweight, generic, and robust integration paradigm that requires no architectural modifications to backbone models.

Technology Category

• Reasoning under Uncertainty: Sequential Decision Making
• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Modeling non-item pages' influence
• Enhancing next-item prediction accuracy
• Integrating non-item pages in models

Innovation

• Integrates non-item pages
• Enhances sequential recommendation models
• Improves next-item prediction accuracy