Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Regression Mapping

2,642 views

Published on

Presentation at the CARS Workshop in the context of the Conference of Recommender Systems 2011, held in Chicago.

  • Be the first to comment

Implicit Feedback Recommendation via Implicit-to-Explicit Ordinal Logistic Regression Mapping

  1. 1. Implicit Feedback Recommendation via Implicit-to- Explicit OLR MappingDenis Parra (Pitt), Alexandros Karatzoglou (TID), Xavier Amatriain (TID), Idil Yavuz (Pitt) CARS 2011 October 23rd 2011
  2. 2. Outline• Introduction• Datasets• Models• Results• Discussion• Conclusion
  3. 3. A More Clear Outline• This presentation has, IMHO, 3 sections: 1. Good News 2. Not that Good News 3. Good News• Which represent, respectively 1. Results of first study on last.fm presented in UMAP 2011  2. Initial results of the study we present here  3. Expected Results after analysis of 2. (once I finish my comps) – and your feedback! 
  4. 4. Introduction• Most of recommender system approaches rely on explicit information of the users, but…• Explicit feedback: scarce (people are not especially eager to rate or to provide personal info)• Implicit feedback: Is less scarce, but (Hu et al., 2008) There’s no negative feedback … and if you watch a TV program just once or twice? Noisy … but explicit feedback is also noisy (Amatriain et al., 2009) Preference & Confidence … we aim to map the I.F. to preference (our main goal) Lack of evaluation metrics … if we can map I.F. and E.F., we can have a comparable evaluation7/12/2011 Parra, Amatriain "Walk the Talk" 4
  5. 5. Section I : Good News • Last.fm User Study• Linear regression results
  6. 6. Recalling the 1st study (1/5)• Last.fm users (114 in total after filtering)• For each user, we crawled all the albums they listened to send them a personalized survey
  7. 7. Recalling the 1st study (2/5)• What items should they rate? Item (album) sampling: – Implicit Feedback (IF): playcount for a user on a given album. Changed to scale [1-3], 3 means being more listened to. – Global Popularity (GP): global playcount for all users on a given album [1-3]. Changed to scale [1-3], 3 means being more listened to. – Recentness (R) : time elapsed since user played a given album. Changed to scale [1-3], 3 means being listened to more recently. 7/12/2011 Parra, Amatriain "Walk the Talk" 7
  8. 8. Recalling the 1st study (3/5)• Demographics Survey + Rating 100 albums7/12/2011 Parra, Amatriain "Walk the Talk" 8
  9. 9. Recalling the 1st study (4/5)• Gender• Age• Country• Hours per week spent on internet [int_hrs_per_week]• Hours per week listening to music online [msc_hrs_per_week]• Number of concerts per year [conc_per_year]• Do you read specialized music blogs or magazines? [blogs_mag]• Do you have experience evaluating music online? [rate_music]• How frequently do you buy physical music records? [buy_records]• How frequently do you buy music online? [buy_online]• Do you prefer listening to single tracks, whole albums or either way? [track_or_CD]7/12/2011 Parra, Amatriain "Walk the Talk" 9
  10. 10. Recalling the 1st study (5/5)• Prediction of rating by multiple Linear Regression evaluated with RMSE.• Results showed that Implicit feedback (play count of the album by a specific user) and recentness (how recently an album was listened to) were important factors, global popularity had a weaker effect.• Results also showed that listening style (if user preferred to listen to single tracks, CDs, or either) was also an important factor, and not the other ones.
  11. 11. ... but• Linear Regression didn’t account for the nested nature of ratings User 1 User n ...1 3 5 3 0 4 5 2 2 1 5 4 3 2 3 2 1 0 4 5 25 4 3 21 3 5• And ratings were treated as continuous, when they are actually ordinal.
  12. 12. So, Ordinal Logistic Regression!• Actually Mixed-Effects Ordinal Multinomial Logistic Regression• Mixed-effects: Nested nature of ratings• We obtain a distribution over ratings (ordinal multinomial) per each pair USER, ITEM -> we predict the rating using the expected value.• … And we can compare the inferred ratings with a method that directly uses implicit information (playcounts) to recommend ( by Hu, Koren et al. 2007)
  13. 13. Model [to predict rating user x item]• Model• Predicted value
  14. 14. Final MELR Model with 4 fixed effects
  15. 15. Section II : Not that Good News • Datasets I and II• Results measured as MAP and nDCG.
  16. 16. Datasets• D1: users, albums, if, re, gp, ratings, demographics/consumption• D2: users, albums, if, re, gp, NO RATINGS.
  17. 17. Experiments• First step: build MELR model using D1• For D1 and D2: split dataset in 5 parts to perform a 5-fold cross validation
  18. 18. Results
  19. 19. Section III: Expected Good News• After Analyzing our data/process
  20. 20. Lessons / Challenges (1/2)Problem/ Challenge1. Ground truth: Playcounts of albums or tracks?2. Quantization of playcounts (implicit feedback),recentness, and overall number of listeners of an album(global popularity) [1-3] scale v/s raw playcounts3. Defining Relevancy of recommended elements (tocompare with the raw playcounts)
  21. 21. Lessons / Challenges (2/2)Problem/ Challenge4. Additional/Alternative metrics for evaluation [MAPand nDCG used in the paper]5. New Survey (In order to deal with the issues ofidentifying “actual” relevancy in dataset2)6. Significance of level-2 variables: track_or_CD (study1 v/s 2, where concerts_per_year was significant)
  22. 22. … so• Lots of work to do [after my comps]• Questions, Suggestions?
  23. 23. Is this the end?7/12/2011 Parra, Amatriain "Walk the Talk" 23
  24. 24. Thanks!• Denis Parra dap89@pitt.edu
  25. 25. Backup slides
  26. 26. Complete Results for D2 AVG (MAP) AVG(nDCG) SD (MAP) SD(nDCG)Koren 0.101428473 0.271841949 0.001504383 0.001906666KorenLog 0.123444659 0.295368576 0.002105906 0.002239792logit_3 0.12225702 0.294351155 0.000868738 0.001100289popularity 0.01777665 0.136672774 0.000937768 0.00086512linear_2 0.123417895 0.295026219 0.001830371 0.001554675linear_3 0.122317675 0.294211465 0.001744534 0.00212961
  27. 27. Distribution of ratings
  28. 28. Actual Distribution of ratings
  29. 29. Some Intuition About the Results• Distributions of ratings in both datasets
  30. 30. M2:implicitfeedback &recentness 4 Regression Analysis M1: implicit feedbackM4: M3: implicitInteraction of feedback,implicit recentness,feedback & globalrecentness popularity • Including Recentness increases R2 in more than 10% [ 1 -> 2] • Including GP increases R2, not much compared to RE + IF [ 1 -> 3] • Not Including GP, but including interaction between IF and RE improves the variance of the DV explained by the regression model. [ 2 -> 4 ] 7/12/2011 Parra, Amatriain "Walk the Talk" 30
  31. 31. 4.1 Regression AnalysisModel RMSE1 RMSE2User average 1.5308 1.1051M1: Implicit feedback 1.4206 1.0402M2: Implicit feedback + recentness 1.4136 1.034M3: Implicit feedback + recentness + global popularity 1.4130 1.0338M4: Interaction of Implicit feedback * recentness 1.4127 1.0332• We tested conclusions of regression analysis by predicting the score, checking RMSE in 10- fold cross validation.• Results of regression analysis are supported.7/12/2011 Parra, Amatriain "Walk the Talk" 31
  32. 32. 4.2 Regression Analysis – Track or AlbumModel Tracks Tracks/ Albums AlbumsUser average 1.1833 1.1501 1.1306M1: Implicit feedback 1.0417 1.0579 1.0257M2: Implicit feedback + recentness 1.0383 1.0512 1.0169M3: Implicit feedback + recentness + global 1.0386 1.0507 1.0159popularityM4: Interaction of Implicit feedback * recentness 1.0384 1.049 1.0159 • Including this variable that seemed to have an effect in the general analysis, helped to improve accuracy of the model 7/12/2011 Parra, Amatriain "Walk the Talk" 32
  33. 33. Is this the end?7/12/2011 Parra, Amatriain "Walk the Talk" 33

×