KnoChain: Knowledge-Aware Recommendation for Alleviating Cold Start in Sustainable Procurement

When new purchasers or products are added in the supply chain management system, the recommendation system will face severe challenges of data sparsity and cold start. A knowledge graph that can enrich the representations of both procurement managers and products offers a promising pathway to mitigate the challenges. This paper proposes a knowledge-aware recommendation network for supply chain management, called KnoChain. The proposed model refines purchaser representations through outward propagation along knowledge graph links and enhances product representations via inward aggregation of multi-hop neighbourhood information. This dual approach enables the simultaneous discovery of purchasers’ latent preferences and products’ underlying characteristics, facilitating precise and personalised recommendations. Extensive experiments on three real-world datasets demonstrate that the proposed method consistently outperforms several state-of-the-art baselines, achieving average AUC improvements of 9.36%, 5.91%, and 8.81%, and average accuracy gains of 8.56%, 6.27%, and 8.67% on the movie, book, and music datasets, respectively. These results underscore the model’s potential to enhance recommendation robustness in supply chain management. The KnoChain framework proposed in this article combines purchaser-aware attention with knowledge graphs to improve the accuracy of purchaser SKU matching. The method can help enhance supply chain resilience and reduce returns caused by over-ordering, inventory backlog, and incorrect procurement. In addition, the model provides interpretable recommendation paths based on the knowledge graph, which improves trust and auditability for procurement personnel and helps balance environmental and operational costs.