GReS: Graphical Cross-domain Recommendation for Supply Chain Platform

TL;DR

This paper introduces GReS, a novel graphical cross-domain recommendation model that leverages hierarchical commodity structures in supply chain platforms to improve recommendation accuracy, outperforming existing methods.

Contribution

GReS uniquely incorporates hierarchical graph structures and combines GCN and BERT for embedding, addressing data sparsity in supply chain platform recommendations.

Findings

GReS significantly outperforms state-of-the-art methods in experiments.

Hierarchical graph modeling improves recommendation performance.

Combining GCN and BERT enhances embedding quality.

Abstract

Supply Chain Platforms (SCPs) provide downstream industries with numerous raw materials. Compared with traditional e-commerce platforms, data in SCPs is more sparse due to limited user interests. To tackle the data sparsity problem, one can apply Cross-Domain Recommendation (CDR) which improves the recommendation performance of the target domain with the source domain information. However, applying CDR to SCPs directly ignores the hierarchical structure of commodities in SCPs, which reduce the recommendation performance. To leverage this feature, in this paper, we take the catering platform as an example and propose GReS, a graphical cross-domain recommendation model. The model first constructs a tree-shaped graph to represent the hierarchy of different nodes of dishes and ingredients, and then applies our proposed Tree2vec method combining GCN and BERT models to embed the graph for recommendations. Experimental results on a commercial dataset show that GReS significantly outperforms state-of-the-art methods in Cross-Domain Recommendation for Supply Chain Platforms.