Fighting Choice Overload: Using Recommender Systems for a Better Experience - EuroIA2012, Rome

Transcript

1. Fighting Choice Overload Using Recommender Systems for a Better Experience Pónya Judit FatDUX Budapest EuroIA 2012, Rome September 29, 2012.
2. Judit Pónya @ptxster
3. find search
4. ! !
5. Aspects ▪ Recommendation instead of “word-of-mouth”
6. Aspects ▪ Recommendation instead of “word-of-mouth” ▪ Personalization as users have different preferences and goals
7. Aspects ▪ Recommendation instead of “word-of-mouth” ▪ Personalization as users have different preferences and goals ▪ Content discovery Help users to find good or useful things without specifically searching for them
8. Aspects ▪ Recommendation instead of “word-of-mouth” ▪ Personalization as users have different preferences and goals ▪ Content discovery Help users to find good or useful things without specifically searching for them ▪ Fighting choice overload Choosing from many alternatives is not an easy task... Don’t let your users give up!
9. When Choice is Demotivating: Can One Desire Too Much of a Good Thing? Iyengar, S. S., & Lepper, M.
10. 3% 30% When Choice is Demotivating: Can One Desire Too Much of a Good Thing? Iyengar, S. S., & Lepper, M.
11. on shelf! tasting booth
13. Don’t let them give up! ▪make it less work to find things ▪provide some solution as soon as possible ▪make it easier to choose
14. 1. The human touch
15. Business Control & Analytics Knowledge Base User Interface Knowledge Processing Application
16. User Interface Business Control & Analytics Knowledge Base Processing Francisco J. Martin (Strands), RecSys2009
17. 2. Focus on content
18. Characteristics of an item Build profile for each item/user based on their properties item
19. Change the focus item !
20. User Behavior Looking for clues to understand preferences & intent
21. 3. Focus on interaction
22. “YouTube Comes To A 5-Star Realization: Its Ratings Are Useless” 1 2 3 4 5 http://techcrunch.com/2009/09/22/youtube-comes-to-a-5-star-realization-its-ratings-are-useless/
23. Events ▪ 1-5 star rating each user would rate only a very small portion of all items
24. Events ▪ 1-5 star rating implicit feedback each user would rate only a very small portion of all items ▪ View page. ▪ Read article for 1-5 minutes. ▪ Come back to page. ▪ Put to cart. ▪ Buy.
25. Don’t make me work.
26. Cold start problem oh, wait....
27. Indi Young http://www.flickr.com/photos/indiyoung/7889928594 I spent like 40 minutes rating movies for Netflix a while ago. When I asked for suggestions, I got this message. Wow, it made my heart drop. I invested all that time, and my preferences were not something Netflix seemed to care about.
28. " Data # Data Processing $ Control % UI
29. Knowledge Base Data quality and quantity matters.
30. Knowledge Processing Application several algorithms in use ▪build model based on data ▪make predictions using the model
31. Business Control
32. User Interface
33. Business Control & Analytics
34. How will itt appear on the user interface? ▪placement ▪visual design ▪good title, giving some explanation
35. Number of recommendations
36. Number of recommendations choosability Stefano Bussolon, EuroIA2011
37. What’s the dealbreaker? item #3278 item #6723 item #5195 item #4981
38. Don’t let it slow down your system! system performance response time (milliseconds) Will it handle millions of recommendation request? Do you have a fallback solution?
39. Widgets & other uses newsletters ▪personalized content ▪target special user group site search ▪modify ranking ?
40. User Interface Business Control & Analytics Knowledge Base Processing Francisco J. Martin (Strands), RecSys2009
41. Don’t let them give up! ▪make it less work to find things ▪provide some solution as soon as possible ▪make it easier to choose
42. Judit Pónya @ptxster jponya@fatdux.com www.fatdux.com Köszönöm!