Providing Naïve Bayesian Classifier-Based Private Recommendations on Partitioned Data
PKDD 2007 Proceedings of the 11th European conference on Principles and Practice of Knowledge Discovery in Databases
Providing predictions on distributed HMMs with privacy
Artificial Intelligence Review
Privacy-preserving eigentaste-based collaborative filtering
IWSEC'07 Proceedings of the Security 2nd international conference on Advances in information and computer security
AdPriRec: a context-aware recommender system for user privacy in MANET services
UIC'11 Proceedings of the 8th international conference on Ubiquitous intelligence and computing
YANA: an efficient privacy-preserving recommender system for online social communities
Proceedings of the 20th ACM international conference on Information and knowledge management
Achieving private recommendations using randomized response techniques
PAKDD'06 Proceedings of the 10th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining
| Hi-index | 0.00 |
Collaborative filtering techniques are widely used by many E-commerce sites for recommendation purposes. Such techniques help customers by suggesting products to purchase using other usersý preferences. Todayýs top-N recommendation schemes are based on market basket data, which shows whether a customer bought an item or not. Data collected for recommendation purposes might be split between different parties. To provide better referrals and increase mutual advantages, such parties might want to share data. Due to privacy concerns, however, they do not want to disclose data. This paper presents a scheme for binary ratings-based top-N recommendation on horizontally partitioned data, in which two parties own disjoint sets of usersý ratings for the same items while preserving data ownersý privacy. If data owners want to produce referrals using the combined data while preserving their privacy, we propose a scheme to provide accurate top-N recommendations without exposing data ownersý privacy. We conducted various experiments to evaluate our scheme and analyzed how different factors affect the performance using the experiment results.