超越共购关系：Allegro平台互补推荐的演进
Beyond Co-purchase Relation: Evolution of Complementary Recommendations at Allegro
- NVIDIA（英伟达）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出部署于Allegro平台的AlleCompanion检索框架，结合类别约束双塔架构与多源互补类别映射ComCat，过滤共购噪声，提升互补推荐效果，服务超2000万活跃用户并带动GMV增长。
AI中文摘要：
当顾客将专业相机加入购物车时，系统应推荐匹配的镜头、通用三脚架还是另一台相机机身？互补产品推荐对构建完整购物篮至关重要，但标准模型往往无法区分仅被共同购买的商品与真正适配的商品。本文提出AlleCompanion：部署在allegro平台的生产级检索框架，该框架将嘈杂的行为信号转化为精确的语义适配性。我们通过结合数据层面的过滤启发式方法与类别约束的双塔架构，缓解大规模共购流量中的固有噪声。在该框架内，类别适配器在嵌入空间中引导模型，将候选商品限制在逻辑互补的范围内。由于大规模建模真实用户行为本质上存在难度，我们引入ComCat——一种多源互补类别映射。ComCat作为转换层，将嘈杂流量中的有意义模式提炼为可维护、可控制的解决方案，整合了专家规则、人在回路反馈、基于大语言模型（LLM）的推理以及统计挖掘。我们的实验结果表明，将显式类别层面的约束与神经架构相结合，可有效过滤共购噪声，生成满足现实用户需求的推荐。该框架每月服务超过2000万活跃用户，在自然发现归因GMV方面实现显著提升，并推动赞助位的可观收入增长。
英文摘要：
When a customer adds a professional camera to their cart, should the system suggest a matching lens, a generic tripod, or another camera body? Complementary Product Recommendation is vital for comprehensive basket building, yet standard models often fail to distinguish between items that are merely bought together and those that truly work together. In this paper, we present AlleCompanion: a production-scale retrieval framework deployed at Allegro.com that transforms noisy behavioural signals into precise semantic compatibility. We mitigate the intrinsic noise in large-scale co-purchase traffic by combining data-level filtering heuristics with a category-constrained Two Tower architecture. Within this framework, the Category Adapter guides the model in the embedding space, constraining candidates within logically complementary boundaries. Since modelling authentic user behaviour at scale is inherently difficult, we introduce ComCat, a multi-source Complementary Categories Mapping. ComCat acts as a translational layer that distils meaningful patterns from noisy traffic into a maintainable and controllable solution, integrating expert rules, human-in-the-loop feedback, LLM-based reasoning, and statistical mining. Our experimental results demonstrate that combining explicit category-level constraints with neural architectures effectively filters out co-purchase noise to surface recommendations that satisfy real-world user needs. Serving over 20 million active users monthly, the framework delivers significant uplifts in attributed GMV for organic discovery and drives substantial revenue growth in sponsored placements.
