Enhancing enterprise knowledge retrieval via cross-domain deep recommendation: a sparse data approach

• Published in: Scientific reports Vol. 15; no. 1; pp. 17507 - 15
• Main Author: Li, Ting
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 20.05.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166; 639/705; Accuracy; CDR-VAE; Cross-domain recommendation; Datasets; Decision making; Deep generative model; Deep learning; Efficiency; Enterprise knowledge retrieval; Graphs; Humanities and Social Sciences; Knowledge management; Knowledge representation; Literature reviews; Methods; multidisciplinary; Optimization; Science; Science (multidisciplinary); Semantics; Sparse data scenarios; Enterprise knowledge retrieval; Cross-domain recommendation; Deep generative model; CDR-VAE; Sparse data scenarios
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-01999-9

Enterprise knowledge retrieval faces challenges like sparse data and inefficient cross-domain knowledge transfer, hindering traditional methods. To address this, we develop a cross-domain recommendation model (CDR-VAE), combining a hybrid autoencoder with domain alignment, and test its effectiveness on an enterprise dataset and the Movies&Books benchmark. At a top-5 recommendation length, CDR-VAE scores HR = 0.642, Recall = 0.432, NDCG = 0.715, outperforming existing models. Removing shared latent representations reduces HR to 0.701, proving their necessity for cross-domain learning. In enterprise applications, high-activity users favor technical reports (0.903), while low-activity users shift toward cross-domain content like industry standards (0.701), confirming the model’s robustness in sparse scenarios. CDR-VAE successfully tackles sparsity and cross-domain barriers, advancing enterprise knowledge management. This work provides theoretical and practical insights for deep learning-based recommendation systems in data-scarce environments.