1. Private Distributed Collaborative Filtering Using Estimated Concordance Measures Neal Lathia Dr. Stephen Hailes Dr. Licia Capra Department of Computer Science University College London [email_address]
5. solution: distributed collaborative filtering a b c d 4 3 3 ? a b c d 4 ? 3 4 Step 1 : Profile Similarity (Correlation) Step 2 : k-Nearest Neighbours Step 3 : Recommendation Aggregation similarity
7. problem: who do you trust? how do we bootstrap cooperation when we do not know how much to trust the community? solution: estimate profile similarity with privacy
10. privacy… … the right to control the flow of your personal information
11. private information a b c d 4 ? 3 4 A rating r a,i by user a for item i The full set of ratings r a for user a The mean rating r mean of user a The number of items user a has rated
13. but even if we did trust some people… … similarity measures are not transitive ? privacy
14.
15. concordance: definition define : d a,i = r a,i - r mean measure similarity according to proportion of agreement: classify ratings into one of three groups
27. private collaborate filtering: the idea a b c d 4 3 3 ? a b c d 4 ? 3 4 a b c d 5 3 2 4 C, D, T estimate similarity by upper/lower bounds of overlap (full details in paper)
32. evaluation: Highest error when dataset is: small and very sparse How well do estimated coefficients work to generate recommendations ? 2) return to the netflix dataset..
36. Private Distributed Collaborative Filtering using Estimated Concordance Measures Neal Lathia Dr. Stephen Hailes Dr. Licia Capra Department of Computer Science University College London [email_address] related work, research: mobblog.cs.ucl.ac.uk