Hash-based lightweight recommendation in edge computing for privacy-preserving sport communities

With the rapid advancement of social development, personalization has become a defining feature of modern digital services, shaping user preferences and behaviors across various domains. In this context, sport communities represent a typical scenario where users seek tailored recommendations for sport-related items while demanding strict privacy protection. However, safeguarding user identities and preference data remains a major challenge for recommendation systems, particularly in resource-constrained environments. To address this issue, we propose a hash-based lightweight and distributed recommendation framework in edge computing, which integrates hash encoding with edge-assisted distributed computation to achieve an effective balance between privacy preservation and recommendation accuracy. Specifically, hash functions are employed to anonymize user preferences, while edge nodes collaboratively perform recommendation tasks with reduced communication overhead, enabling efficient and scalable deployment. Extensive experiments validate the effectiveness of our approach, showing superior performance compared to existing methods in both recommendation accuracy and privacy protection, while significantly lowering computational and transmission costs.