1. Shanda Innovations Context-aware Ensemble of Multifaceted Factorization Models for Recommendation Kevin Y. W. Chen

2. Performance 0.43959(public score)/0.41874(private score) 2 nd place  Honorable Mention

3. New Challenges Richer features in the social networks –follower/followee, actions Items are complicate –items are specific users Cold-start problem –77.1% users do not have training records Training data is quite noisy –ratio of negative samples is 92.82%

4. Outline Preprocessing –denoise –supplement Pairwise Training –Max-margin optimization problem Multifaceted Factorization Models –Extend the SVD++ Context-aware Ensemble –Logistic Regression

5. Preprocess: Session analysis Negative : Positive = 92 : 8 ? –not all the negative ratings imply that the users rejected to follow the recommended items Eliminating these “omitted” records is necessary –These negative samples can not indicate users' interests

6. Preprocess: Session analysis Session slicing according to the time interval Select the right samples from the right session:

7. Preprocess: Session analysis Training dataset after preprocessing –Negative: 67,955,449 -> 7,594,443 (11.2%) –Positive: 5,253,828 ->4,999,118 Benefits –improve precision (0.0037) –reduce computational complexity

8. Pairwise-training MAP –pairwise ranking job Training pair –(u, i) and (u, j) Objective function

9. Preprocess: Supply positive samples Lack of positive samples –An ideal pairwise training requires a good balance between the number of negative and positive samples Choose the users –users who have a far smaller number of positive samples than negative samples Generate the positive samples –Figure out from social graphs

10. The procedure of data preprocessing

11. Multifaceted Factorization Models Latent Factor Model –stochastic gradient descent MFM extends the SVD++ –integrate all kinds of valuable features in social networks

12. MFM: Demographic features User and item profiles –age(u), age(i) –gender(u), gender(i) –tweetnum(u) Combinations –uid*gender(i) –uid*age(i) –gender(u)*iid –age(u)*iid

13. MFM: Integrate Social Relationships Influence of social relations Cold start: –77.1% users do not have any rating records in the training set User feature vector: –Incorporate SNS relations and actions Bring significant improvement –MAP: 0.3495 ->0.3688 ->0.3701

14. MFM: Utilizing Keywords and Tags Share common interests –explicit feedbacks User feature vectors:

15. MFM: Date-Time Dependent Biases Users' action differs when time changes The popularities of items change over time

16. k-Nearest Neighbors Similar to SVD++ Find the neighbors –calculate the distance based on Keywords and tags Intersection of explicit and implicit feedbacks

17. Ensemble When will the user follow an item? –pay attention to the item –be interested in the item User behavior modeling –predict whether the user noticed the recommendation area at that time User interest modeling –a item meet the user’s tastes -- MFM

18. User Behavior Modeling Durations of users on each recommendation are very valuable clues Context of durations

19. Experiment

21. The framework

22. Summary A proper data preprocessing is necessary Pairwise training (top-N recommendation) Social relations and actions can be used as implicit feedbacks Integrate all kinds of valuable features Users' interests and users' behaviors are both need to be considered

23. Shanda Innovations Team Yunwen Chen, Zuotao Liu, Daqi Ji, Yingwei Xin, Wenguang Wang, Lu Yao, Yi Zou

24. Kevin Y. W. Chen Shanda Innovations kddchen@gmail.com THANK YOU !

25. Q&A Kevin Y. W. Chen Shanda Innovations kddchen@gmail.com