DeepAffinity：基于小语言模型的电商领域长期属性偏好预测
DeepAffinity: Long-Term Aspect Preference Prediction in eCommerce using Small Language Models
- eBay Inc.（亿贝公司）
- Ben-Gurion University（本-古里安大学）
- DREAM group（DREAM集团）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对电商用户属性偏好预测任务，提出DeepAffinity模型，利用带结构化提示的小语言模型及专用预测头，在跨国电商平台上提升了推荐质量，性能优于标准生成式微调方法。
AI中文摘要：
我们探索预测电商用户对品牌、尺寸、颜色等产品属性的偏好，该任务被定义为属性亲和度（Aspect Affinity）。解决此任务可提升对用户的理解，实现推荐、搜索及营销场景下的细粒度个性化。我们将属性亲和度建模为时间预测任务：根据用户按时间排序的交互历史，预测其未来的属性选择，捕捉超出当前会话的演变长期偏好。为此，我们提出DeepAffinity，该模型利用带有结构化提示的小语言模型（Small Language Models，SLMs），以及针对此任务微调的专用预测头。实验表明，DeepAffinity的性能优于标准生成式微调方法，而通用开源大语言模型（LLMs）在无任务特定微调时表现不佳，凸显其在建模微妙行为方面的局限性。最终，DeepAffinity提升了某大型跨国电商平台的推荐质量。
英文摘要：
We explore predicting eCommerce user preferences for product aspects such as brand, size, and color - a task we define as Aspect Affinity. Solving this task improves customer understanding and enables fine-grained personalization in recommendation, search, and marketing. We frame Aspect Affinity as a temporal prediction task: forecasting a users future aspect choices from their time-ordered interaction history, capturing long-term preferences that evolve beyond the current session. To this end, we propose DeepAffinity, which leverages Small Language Models (SLMs) with structured prompts and specialized prediction heads fine-tuned for this task. We show DeepAffinity outperforms standard generative fine-tuning methods, while general-purpose open-source LLMs perform poorly without task-specific tuning, highlighting their limits in modeling nuanced behavior. Finally, DeepAffinity enhances recommendation quality on a large-scale multinational eCommerce platform.
