Combining social network and collaborative filtering for personalised manufacturing service recommendation

Owing to the rapid proliferation of Web service technologies in cross-enterprise manufacturing collaborations, information overload is becoming a major barrier that hinders the effective discovery of the shared manufacturing services provided by collaborative partners for supply chain deployment. Thus, we aimed to identify a different approach for discovering manufacturing services by making personalised service recommendations that are suited to the specific needs of active service users based on usage data from previous retrievals made by past service users. The proposed approach combines social network and collaborative filtering techniques in a unified framework to predict the missing Quality of Service (QoS) values of manufacturing services for an active service user, thereby improving the effectiveness of personalised QoS-aware service recommendations. The social network explores the usage of preference and tagging relationships among service users and manufacturing services in making personalised recommendation, which alleviates the data sparsity and the cold start problems that hinder the traditional collaborative filtering techniques. A case study and experimental evaluation demonstrate that the proposed approach can achieve the practicality and accuracy to personalised manufacturing service recommendations in a real application.