一个模型搞定三种推荐，高效适配电商多元需求
Suggest, Complement, Inspire: Story of Two Tower Recommendations at Allegro.com
- 基于双塔架构，用文本和结构化属性表征商品
- 三类推荐任务仅需调整少量组件即可实现
- 两年A/B测试验证提升用户参与与收益
构建大规模电商平台推荐系统面临三大挑战：跨数十个位置的通用架构设计、高昂维护成本以及高度动态的商品目录管理。本文介绍在欧洲最大本土电商平台Allegro.com部署的统一内容型推荐系统。该系统基于主流双塔检索框架，利用文本和结构化属性表示商品，通过近似最近邻搜索实现高效检索。我们展示同一模型架构可通过微调模型或服务逻辑中的少量组件，灵活支持三类推荐任务：相似商品搜索、互补商品推荐与灵感内容发现。两年间在桌面端和移动端的大量A/B测试证实，该方案显著提升了用户参与度与利润相关指标。结果表明，一种灵活可扩展的架构可在极低维护成本下满足多样化的用户意图。
原文摘要 · Abstract (English)
Building large-scale e-commerce recommendation systems requires addressing three key technical challenges: (1) designing a universal recommendation architecture across dozens of placements, (2) decreasing excessive maintenance costs, and (3) managing a highly dynamic product catalogue. This paper presents a unified content-based recommendation system deployed at Allegro.com, the largest e-commerce platform of European origin. The system is built on a prevalent Two Tower retrieval framework, representing products using textual and structured attributes, which enables efficient retrieval via Approximate Nearest Neighbour search. We demonstrate how the same model architecture can be adapted to serve three distinct recommendation tasks: similarity search, complementary product suggestions, and inspirational content discovery, by modifying only a handful of components in either the model or the serving logic. Extensive A/B testing over two years confirms significant gains in engagement and profit-based metrics across desktop and mobile app channels. Our results show that a flexible, scalable architecture can serve diverse user intents with minimal maintenance overhead.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。