A Practical Two-stage Ranking Framework for Cross-market Recommendation

TL;DR

This paper presents a practical two-stage framework for cross-market recommendation that leverages multiple features, graph neural networks, traditional models, and ensemble methods to improve product recommendations in resource-scarce markets, validated by experiments and competition success.

Contribution

It introduces a comprehensive two-stage recommendation framework combining deep graph models, traditional methods, and ensemble learning specifically for cross-market scenarios, with demonstrated effectiveness.

Findings

Achieved second place in WSDM CUP 2022 cross-market recommendation contest.

Validated the effectiveness of combining deep graph models with traditional recommenders.

Demonstrated superior performance of tree-based ensembling methods like LightGBM.

Abstract

Cross-market recommendation aims to recommend products to users in a resource-scarce target market by leveraging user behaviors from similar rich-resource markets, which is crucial for E-commerce companies but receives less research attention. In this paper, we present our detailed solution adopted in the cross-market recommendation contest, i.e., WSDM CUP 2022. To better utilize collaborative signals and similarities between target and source markets, we carefully consider multiple features as well as stacking learning models consisting of deep graph recommendation models (Graph Neural Network, DeepWalk, etc.) and traditional recommendation models (ItemCF, UserCF, Swing, etc.). Furthermore, We adopt tree-based ensembling methods, e.g., LightGBM, which show superior performance in prediction task to generate final results. We conduct comprehensive experiments on the XMRec dataset, verifying the effectiveness of our model. The proposed solution of our team WSDM_Coggle_ is selected as the second place submission.