A Lightweight Hashing-Based Approach for Privacy-Preserving IOT Service Recommendation

Data about user-service interactions is frequently kept across several dispersed platforms in the context of the Internet of Things (IoT). In order to make a thorough recommendation decision in this scenario, recommender systems must integrate the dispersed user-service interaction data from several platforms, which likely exposes user privacy. Furthermore, the efficiency of recommendations is greatly diminished as user-service interaction records mount up over time. We suggest a lightweight, privacy-preserving service recommendation method called SerRecL2H to address these problems. To efficiently identify customers with similar preferences for precise suggestions, SerRecL2H uses Learning to Hash (L2H) to encapsulate sensitive user-service interaction data into less-sensitive user indices.