Integrated code-mixing improves cross-country ecommerce recommendations
Cross-Country Code-Mixing for Generative Recommendation
Information RetrievalArtificial Intelligence
Summary
E-commerce platforms often struggle to recommend items across different countries because they keep user and item data separate for each market. The authors created a new method called CMRec that mixes recommendation data from multiple countries to share useful information, much like how people switch between languages in conversation. This approach uses a shared codebook to blend data while respecting product and market differences, improving recommendations especially where data is limited. Tests showed CMRec increased orders and advertising revenue on a large e-commerce site.
What this means in practice
- •For e-commerce platform teams: Improve recommendation quality in countries with sparse user data by mixing cross-country behavioral information in one model.
- •For online advertising managers: Increase advertising revenue by leveraging mixed-country user-item interactions to optimize targeted ads and product recommendations.
Authors
Yuan Gao, Hao Deng, Haibo Xing, Yi Xu, Lingyu Mu, Jinxin Hu, Yu Zhang, Xiaoyi Zeng
Abstract
Cross-country recommendation on modern e-commerce platforms is typically deployed with disjoint user and item ID spaces across markets, removing the shared anchors that conventional cross-domain methods rely on. Generative recommendation (GR) mitigates this by mapping items into a shared token space and training a unified model, but existing approaches keep behavior sequences strictly country-specific, so knowledge transfer occurs only at the parameter level and remains absent at the data level. Inspired by code-switching corpora in multilingual natural language processing, we propose CMRec, a cross-country GR framework that injects cross-country supervision at the data level via dual-constrained, context-aware code-mixing. CMRec first learns a shared semantic codebook from multi-modal content and behavioral co-occurrence across countries. It then uses this codebook to synthesize mixed-country sequences via token-level substitutions that satisfy both static (content) and dynamic (e.g., price, audience, popularity) constraints. Finally, it introduces a context-aware loss that reweights mixed samples according to their plausibility in the current sequence. Experiments on two real-world multi-country datasets and an online A/B test show that CMRec substantially improves recommendation quality in data-sparse countries while preserving performance in data-rich countries, achieving +1.77% advertising revenue and +2.64% orders on a large-scale e-commerce platform.