On Recommending Category: A Cascading Approach

2025-12-17

AI Summary

Existing e-commerce recommendation systems predominantly focus on item-level prediction, neglecting category-level latent interest modeling—leading to performance degradation under sparse user interactions. To address this, we propose CCRec, the first cascaded categorical recommendation paradigm explicitly designed for category-level recommendation. CCRec overcomes the limitations of naively reusing item-level models by jointly modeling the hierarchical semantic coupling between items and categories. Methodologically, it employs a variational autoencoder (VAE) to encode user-item interaction sequences into latent distributions and subsequently decodes them into category-level preference probabilities. Extensive experiments on multiple real-world e-commerce datasets demonstrate that CCRec significantly outperforms state-of-the-art item-level methods, achieving up to a 12.6% improvement in Recall@10. Moreover, it effectively alleviates cold-start issues and enhances user intent understanding, providing interpretable, fine-grained category-level guidance for downstream recommendation tasks.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recommendation plays a key role in e-commerce, enhancing user experience and boosting commercial success. Existing works mainly focus on recommending a set of items, but online e-commerce platforms have recently begun to pay attention to exploring users' potential interests at the category level. Category-level recommendation allows e-commerce platforms to promote users' engagements by expanding their interests to different types of items. In addition, it complements item-level recommendations when the latter becomes extremely challenging for users with little-known information and past interactions. Furthermore, it facilitates item-level recommendations in existing works. The predicted category, which is called intention in those works, aids the exploration of item-level preference. However, such category-level preference prediction has mostly been accomplished through applying item-level models. Some key differences between item-level recommendations and category-level recommendations are ignored in such a simplistic adaptation. In this paper, we propose a cascading category recommender (CCRec) model with a variational autoencoder (VAE) to encode item-level information to perform category-level recommendations. Experiments show the advantages of this model over methods designed for item-level recommendations.

Problem

• Recommends categories to explore user interests
• Addresses limitations of item-level recommendation models
• Uses VAE to encode items for category prediction

Innovation

• Cascading category recommender model with VAE
• Encodes item-level information for category recommendations
• Addresses differences between item and category-level tasks