A Strategy toward Collaborative Filter Recommended Location Service for Privacy Protection

Area of Science:

• Computer Science
• Data Science
• Cybersecurity

Background:

• Existing location services face significant privacy and security challenges.
• Current recommendation systems often compromise user location data.

Purpose of the Study:

• To propose a novel collaborative filtering recommendation strategy for location services.
• To address privacy and security concerns in location-based services.

Main Methods:

• Users create position profiles from daily location data, preprocessed with density clustering.
• Density prioritization identifies similar user groups for service request responses.
• Collaborative filtering algorithms recommend location services based on profile and point similarity.
• Homomorphic encryption is utilized for secure data transfer.

Main Results:

• The proposed strategy effectively protects user privacy and location data.
• The system demonstrated improved location service recommendations compared to existing methods.
• Real-world location datasets validated the strategy's performance.

Conclusions:

• The developed strategy offers a robust solution for privacy-preserving location recommendations.
• It balances the need for personalized location services with stringent user data protection.
• This approach enhances the security and usability of location-based services.