TEPP: A robust trust-enhanced privacy-preserving quality of service prediction method for web service recommendation

In today’s service-oriented digital environment, ensuring the quality of service (QoS) is crucial, which makes QoS prediction a prominent topic in current research on Web service recommendation. Recently, some existing works have made significant advancements in modeling both users and services. However, several key issues have not been well studied in existing research, including issues related to bilateral trust, user preferences, and privacy protection. To effectively resolve these concerns, we put forward TEPP, a robust trust-enhanced privacy-preserving QoS prediction method for Web service recommendation. First, we evaluate user reputation values through the Dirichlet distribution and integrate user similarity to jointly compute trust values between users, thereby identifying a group of trustworthy and similar users. At the same time, we utilize an exponential mechanism to protect the privacy of user information. Secondly, we calculate the preference similarity between users, taking into account their preferences. Finally, we determine a set of trustworthy similar services by combining the reputation value and similarity of the service providers, and predict missing QoS by a fusion model that integrates the above three methods. To make TEPP more practical and robust in Web service recommendation, we embed a bilateral trust model in TEPP based on evolutionary game theory to constrain and guide users and service providers to honestly participate in the Web service recommendation. Experimental simulation results demonstrate that the proposed scheme not only outperforms existing schemes in prediction accuracy but also can fully motivate both users and service providers to choose trusted strategic behaviors in the Web service recommendation.