Style4Rec: Enhancing Transformer-based E-commerce Recommendation Systems with Style and Shopping Cart Information

2025-01-16

AI Summary

Existing Transformer-based sequential recommendation models struggle to effectively capture users’ real-time purchase intent and overlook both item visual style and dynamic cart state. To address these limitations, this paper proposes a cart-aware multimodal Transformer framework for sequential recommendation. Our method jointly incorporates fine-grained visual style representations—obtained via CLIP fine-tuning—with explicit modeling of cart state, and introduces a novel cart-aware attention mechanism to enhance short-term interest modeling and cross-modal semantic alignment. The entire model is trained end-to-end. Extensive experiments on a real-world e-commerce dataset demonstrate significant improvements over state-of-the-art methods: Hit Rate@5 increases by 5.4% to 0.735, NDCG@5 by 8.0% to 0.674, and MRR@5 by 9.5% to 0.654. To the best of our knowledge, this is the first work to explicitly integrate visual style semantics and dynamic cart state into a Transformer-based sequential recommender.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• 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

Understanding users' product preferences is essential to the efficacy of a recommendation system. Precision marketing leverages users' historical data to discern these preferences and recommends products that align with them. However, recent browsing and purchase records might better reflect current purchasing inclinations. Transformer-based recommendation systems have made strides in sequential recommendation tasks, but they often fall short in utilizing product image style information and shopping cart data effectively. In light of this, we propose Style4Rec, a transformer-based e-commerce recommendation system that harnesses style and shopping cart information to enhance existing transformer-based sequential product recommendation systems. Style4Rec represents a significant step forward in personalized e-commerce recommendations, outperforming benchmarks across various evaluation metrics. Style4Rec resulted in notable improvements: HR@5 increased from 0.681 to 0.735, NDCG@5 increased from 0.594 to 0.674, and MRR@5 increased from 0.559 to 0.654. We tested our model using an e-commerce dataset from our partnering company and found that it exceeded established transformer-based sequential recommendation benchmarks across various evaluation metrics. Thus, Style4Rec presents a significant step forward in personalized e-commerce recommendation systems.

Problem

• Transformer-based recommendation systems
• image style processing
• shopping cart information integration

Innovation

• Style4Rec
• Transformer-based Recommendation System
• Product Style and Cart Integration