DAIAN: Deep Adaptive Intent-Aware Network for CTR Prediction in Trigger-Induced Recommendation

2026-02-15

AI Summary

This work addresses the intent myopia in trigger-based recommendation caused by over-reliance on trigger items and the challenge of sparse ID-based interactions that hinder effective user intent modeling. To overcome these limitations, we propose a dynamic multi-intent adaptive deep recommendation framework. Our approach learns personalized intent representations by analyzing the association between user clicks and trigger items, while also uncovering diverse intents from historical behaviors. We further design a hybrid augmentation mechanism that integrates item IDs with semantic features to enhance item similarity modeling, and introduce an intent-adaptive selection module to refine CTR prediction. Extensive experiments on both public and industrial-scale e-commerce datasets demonstrate that the proposed method significantly outperforms existing baselines, achieving substantial improvements in trigger-based recommendation performance.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Learning Preferences or Rankings

Application Category

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

Abstract

Recommendation systems are essential for personalizing e-commerce shopping experiences. Among these, Trigger-Induced Recommendation (TIR) has emerged as a key scenario, which utilizes a trigger item (explicitly represents a user's instantaneous interest), enabling precise, real-time recommendations. Although several trigger-based techniques have been proposed, most of them struggle to address the intent myopia issue, that is, a recommendation system overemphasizes the role of trigger items and narrowly focuses on suggesting commodities that are highly relevant to trigger items. Meanwhile, existing methods rely on collaborative behavior patterns between trigger and recommended items to identify the user's preferences, yet the sparsity of ID-based interaction restricts their effectiveness. To this end, we propose the Deep Adaptive Intent-Aware Network (DAIAN) that dynamically adapts to users'intent preferences. In general, we first extract the users'personalized intent representations by analyzing the correlation between a user's click and the trigger item, and accordingly retrieve the user's related historical behaviors to mine the user's diverse intent. Besides, sparse collaborative behaviors constrain the performance in capturing items associated with user intent. Hence, we reinforce similarity by leveraging a hybrid enhancer with ID and semantic information, followed by adaptive selection based on varying intents. Experimental results on public datasets and our industrial e-commerce datasets demonstrate the effectiveness of DAIAN.

Problem

• Trigger-Induced Recommendation
• Intent Myopia
• CTR Prediction
• Sparse Interaction
• User Intent

Innovation

• Trigger-Induced Recommendation
• Intent-Aware Modeling
• Adaptive Intent Selection
• Hybrid Similarity Enhancement
• CTR Prediction