Market-Aware Models for Efficient Cross-Market Recommendation

TL;DR

This paper introduces market-aware models for cross-market recommendation that use market embeddings to improve efficiency and effectiveness over meta-learning approaches, especially in global settings.

Contribution

The paper proposes market-aware models that directly incorporate market embeddings, offering a simpler and more resource-efficient alternative to meta-learning in cross-market recommendation tasks.

Findings

MA models outperform market-unaware models in 85% of pairwise cases on nDCG@10.

MA models require only 15% of the training time compared to meta-learning models.

In the global setting, MA models outperform market-unaware models and are competitive with meta-learning methods.

Abstract

We consider the cross-market recommendation (CMR) task, which involves recommendation in a low-resource target market using data from a richer, auxiliary source market. Prior work in CMR utilised meta-learning to improve recommendation performance in target markets; meta-learning however can be complex and resource intensive. In this paper, we propose market-aware (MA) models, which directly model a market via market embeddings instead of meta-learning across markets. These embeddings transform item representations into market-specific representations. Our experiments highlight the effectiveness and efficiency of MA models both in a pairwise setting with a single target-source market, as well as a global model trained on all markets in unison. In the former pairwise setting, MA models on average outperform market-unaware models in 85% of cases on nDCG@10, while being time-efficient - compared to meta-learning models, MA models require only 15% of the training time. In the global setting, MA models outperform market-unaware models consistently for some markets, while outperforming meta-learning-based methods for all but one market. We conclude that MA models are an efficient and effective alternative to meta-learning, especially in the global setting.