Modeling Behavioral Intensity and Transitions for Generative Recommendation

2026-04-27

AI Summary

This work addresses the limitations of existing generative multi-behavior recommendation methods, which typically treat diverse user behaviors uniformly and thus fail to capture inter-behavior intensity differences and state transition patterns. To overcome this, the authors propose BITRec, a novel framework that explicitly distinguishes exploratory from committed behavior trajectories through Hierarchical Behavior Aggregation (HBA) and incorporates a learnable Transition Relation Encoding (TRE) mechanism to model dynamic dependencies among behaviors. By moving beyond conventional unified attention mechanisms, BITRec achieves substantial performance gains across four large-scale real-world datasets. Notably, it improves MRR by up to 22.79% on the Tmall dataset and boosts HR@10 and NDCG@10 by 17.83% and 17.55%, respectively, on the Taobao dataset.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Data Mining & Knowledge Management: Recommender Systems
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Multi-behavior recommendation aims to predict user conversions by modeling various interaction types that carry distinct intent signals. Recently, generative sequence modeling methods have emerged as an important paradigm for multi-behavior recommendation by achieving flexible sequence generation. However, existing generative methods typically treat behaviors as auxiliary token features and feed them into unified attention mechanisms. These models implicitly assume uniform activation of dependencies among historical behaviors, thereby failing to discern differences in intensity or capture transition patterns. To address these limitations, we propose BITRec, a novel generative multi-behavior recommendation framework that introduces structured behavioral modeling through selective dependency activation. BITRec incorporates (i) Hierarchical Behavior Aggregation (HBA), which explicitly models behavioral intensity differences through separated exploration and commitment pathways, and (ii) Transition Relation Encoding (TRE), which encodes transition structures through explicit learnable relation matrices. Experiments on four large-scale datasets (RetailRocket, Taobao, Tmall, Insurance Dataset) with millions of interactions achieve consistent improvements of 15-23% across multiple metrics, with peak gains of 22.79% MRR on Tmall and 17.83% HR@10, 17.55% NDCG@10 on Taobao.

Problem

• multi-behavior recommendation
• behavioral intensity
• behavior transitions
• generative recommendation
• sequence modeling

Innovation

• Generative Recommendation
• Multi-behavior Modeling
• Behavioral Intensity
• Transition Patterns
• Selective Dependency Activation