Recommending Composite Items Using Multi-Level Preference Information: A Joint Interaction Modeling Approach

2026-01-26

AI Summary

This work addresses the challenge of effectively integrating multi-granularity user preferences and domain knowledge in composite item recommendation. To this end, we propose JIMA, a novel method that, for the first time, jointly models high-order interactions between atomic and composite items alongside structured domain rules—such as stylistic compatibility—within a unified framework. JIMA synergistically combines deep learning with collaborative filtering through a multi-level interaction architecture, seamlessly incorporating fine-grained behavioral data and expert knowledge to explicitly capture cross-granularity preference relationships. Extensive experiments across multiple simulated, offline, and real-world online scenarios demonstrate that JIMA significantly outperforms state-of-the-art baselines, achieving superior performance in both recommendation accuracy and practical utility.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

With the advancement of machine learning and artificial intelligence technologies, recommender systems have been increasingly used across a vast variety of platforms to efficiently and effectively match users with items. As application contexts become more diverse and complex, there is a growing need for more sophisticated recommendation techniques. One example is the composite item (for example, fashion outfit) recommendation where multiple levels of user preference information might be available and relevant. In this study, we propose JIMA, a joint interaction modeling approach that uses a single model to take advantage of all data from different levels of granularity and incorporate interactions to learn the complex relationships among lower-order (atomic item) and higher-order (composite item) user preferences as well as domain expertise (e.g., on the stylistic fit). We comprehensively evaluate the proposed method and compare it with advanced baselines through multiple simulation studies as well as with real data in both offline and online settings. The results consistently demonstrate the superior performance of the proposed approach.

Problem

• composite item recommendation
• multi-level preference
• user preference modeling
• recommender systems
• fashion outfit

Innovation

• composite item recommendation
• multi-level preference
• joint interaction modeling
• hierarchical user preference
• domain knowledge integration