Download
recommender systems n.
Skip this Video
Loading SlideShow in 5 Seconds..
Recommender Systems PowerPoint Presentation
Download Presentation
Recommender Systems

Recommender Systems

4 Vues Download Presentation
Télécharger la présentation

Recommender Systems

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

  1. Recommender Systems Robin Burke DePaul University Chicago, IL

  2. About myself • PhD 1993 Northwestern University • Intelligent Multimedia Retrieval • 1993-1998 • Post-doc at University of Chicago • Kristian Hammond • Helped found Recommender, Inc. • became Verb, Inc. • 1998-2000 • Dir. of Software Development • Adjunct at University of California, Irvine • 2000-2002 • California State University, Fullerton • 2002-present • DePaul University

  3. My Interests • Memory • How do we remember the right thing at the right time? • Why is it that computers are so bad at this? • How does knowledge of different types shape the activity of memory?

  4. Organization • 3 days • 21 hours • Not me talking all the time! • Partners • For in-class activities • For coding labs • For labs • Must be one laptop per pair • Using Eclipse / Java

  5. Activity 1 • With your partner • One person should recommend a movie or DVD to the other • asking questions as necessary • in the end, you should be confident that they are right • No right or wrong way to do this! • Take note • the questions you ask • the reasons for the recommendation

  6. Discussion • Recommender • What did you have to ask? • How did you use this information? • Recommendee • What made you sure the recommendation was good?

  7. Example: Amazon.com

  8. Product similarity

  9. Market-basket analysis

  10. Profitability analysis

  11. Sequential pattern mining

  12. Application: Recommender.com

  13. Similar movies

  14. Applying a critique

  15. New results

  16. Knowledge employed • Similarity metric • what makes something "alike"? • # of features in common is not sufficient • Movies • genres of movies • types of actors • directorial styles • meaning of ratings • NR could mean adult, but it could just be a foreign movie

  17. This class Tuesday • 8:00 – 10:30 • 10:45 – 13:00 • 15:00 – 18:00 Wednesday • 8:00 – 10:00 • 10:15 – 13:00 • 17:00 – 19:00 Thursday • 8:00 – 11:00 • 14:30 – 16:00 • 18:00 – 20:00

  18. Roadmap • Session A: Basic Techniques I • Introduction • Knowledge Sources • Recommendation Types • Collaborative Recommendation • Session B: Basic Techniques II • Content-based Recommendation • Knowledge-based Recommendation • Session C: Domains and Implementation I • Recommendation domains • Example Implementation • Lab I • Session D: Evaluation I • Evaluation • Session E: Applications • User Interaction • Web Personalization • Session F: Implementation II • Lab II • Session G: Hybrid Recommendation • Session H: Robustness • Session I: Advanced Topics • Dynamics • Beyond accuracy

  19. Recommender Systems • Wikipedia: • Recommendation systems are programs which attempt to predict items(movies, music, books, news, web pages) that a user may be interested in, given some information about the user's profile. • My definition • Any system that guides the user in a personalized way to interesting or useful objects in a large space of possible options or that produces such objects as output.

  20. Historical note • Used to be a more restrictive definition • “people provide recommendations as inputs, which the system then aggregates and directs to appropriate recipients” (Resnick & Varian 1997)

  21. Aspects of the definition • basis for recommendation • personalization • process of recommendation • interactivity • results of recommendation • interest / useful objects

  22. Personalization • Any system that guides the user in a personalized way to interesting or useful objects in a large space of possible options or that produces such objects as output. • Definitions agree that recommendations are personalized • Some might say that suggesting a best-seller to everyone is a form of recommendation • Meaning • the process is guided by some user-specific information • could be a long-term model • could be a query

  23. Interactivity • Any system that guides the user in a personalized way to interesting or useful objects in a large space of possible options or that produces such objects as output. • Many possible interaction styles • query / retrieve • recommendation list • predicted rating • dialog

  24. Results • Any system that guides the user in a personalized way to interesting or useful objects in a large space of possible options or that produces such objects as output. • Recommendation = Search? • Search • a query matching process • given a query • return all items that match it • Recommendation • a need satisfaction process • given a need • return items that are likely to satisfy it

  25. Some definitions • Recommendation • Items • Domain • Users • Ratings • Profile

  26. Recommendation • A prediction of a given user's likely preference regarding an item • Issues • Negative prediction • Presentation / Interface • Notation • Pred(u,i)

  27. Items • The things being recommended • can be products • can be documents • Assumption • Discrete items are being recommended • Not, for example, contract terms • Issues • Cost • Frequency of purchase • Customizability • Configurations • Notation • I = set of all items • i = an individual item

  28. Recommendation Domain • What is being recommended? • a $0.99 music track? • a $1.9 M luxury condo? • Much depends on the characteristics of the domain • cost • how costly is a false positive? • how costly is a false negative? • portfolio • OK to recommend something that the user has already seen? • compatibility with owned items? • individual vs group • are we recommending something for individual or group consumption? • single item vs configuration • are we recommending a single item or a configuration of items? • what are the constraints that tie configurations together? • constraints • what types of constraints are users likely to impose (hard vs soft)?

  29. Example 1 • Music track (ala iTunes) • low cost • individual • configuration • fit into existing playlist? • portfolio • should not be already owned • constraints • likely to be soft

  30. Example 2 • Course advising • high cost • individual • configuration • must fit with other courses • prerequisites • portfolio • should not have already been taken • constraints • may be hard • graduation requirements • time and day

  31. Example 3 • DVD rental • low cost • group consumption • no configuration issues • portfolio • possible to recommend a favorite title again • Christmas movies • constraints • likely to be soft • some could be hard like maximum allowed rating

  32. Users • People who need / want items • Assumption • (Usually) repeat users • Issues • Portfolio effects • Notation • U = set of all users • u = a particular user

  33. Ratings • A (numeric) score given by a user to a particular item representing the user's preference for that item. • Assumption • Preferences are static (or at least of long duration) • Issues • Multi-dimensional ratings • Context-dependencies • Notation • ru,i = a rating of item i by user u • RU,i = Ri = the ratings of item i by all users

  34. Explicit vs Implicit Ratings • A explicit rating is one that has been provided by a user • via a user interface • An implicit rating is inferred from user behavior • for example, as recorded in web log data • Issues • effort threshold • noise

  35. Collecting Explicit Ratings

  36. Profile • A user profile is everything that the system knows about a particular user • Issues • profile dimensionality • Notation • P = all profiles • Pu = the profile of user u

  37. Knowledge Sources • An AI system requires knowledge • Takes various forms • raw data • algorithm • heuristics • ontology • rule base

  38. In Recommendation • Social knowledge • User knowledge • Content knowledge

  39. Knowledge source: Collaborative • A collaborative knowledge source is one that holds information about peer users in a system • Examples • ratings of items • age, sex, income of other users

  40. Knowledge source: User • A user knowledge source is one that holds information about the current user • the one who needs a recommendation • Example • a query the user has entered • a model of the user's preferences

  41. Knowledge source: Content • A content knowledge source holds information about the items being recommended • Example • knowledge about how items satisfy user needs • knowledge about the attributes of items

  42. Recommendation Knowledge Sources Taxonomy RecommendationKnowledge Collaborative Opinion Profiles Demographic Profiles User Opinions Query Demographics Constraints Requirements Preferences Content Item Features Context DomainKnowledge Means-ends FeatureOntology Contextual Knowledge DomainConstraints

  43. Break

  44. Roadmap • Session A: Basic Techniques I • Introduction • Knowledge Sources • Recommendation Types • Collaborative Recommendation • Session B: Basic Techniques II • Content-based Recommendation • Knowledge-based Recommendation • Session C: Domains and Implementation I • Recommendation domains • Example Implementation • Lab I • Session D: Evaluation I • Evaluation • Session E: Applications • User Interaction • Web Personalization • Session F: Implementation II • Lab II • Session G: Hybrid Recommendation • Session H: Robustness • Session I: Advanced Topics • Dynamics • Beyond accuracy

  45. Recommendation Types • Default (non-personalized) • “Would you like fries with that?” • Collaborative • “Most people who bought hamburgers also bought fries.” • Demographic • “Most 45-year-old computer scientists buy fries.” • Content-based • “You usually buy fries with your burgers.” • Knowledge-based • “A large order of curly fries would really complement the flavor of a Western Bacon Cheeseburger.”

  46. Collaborative • Key knowledge source • opinion database • Process • given a target user, find similar peer users • extrapolate from peer user ratings to the target user

  47. Demographic • Key knowledge sources • Demographic profiles • Opinion profiles • Process • for target user, find users of similar demographic • extrapolate from similar users to target user

  48. Content-based • Key knowledge sources • User’s opinion • Item features • Process • learn a function that maps from item features to user’s opinion • apply this function to new items

  49. Knowledge-based • Key knowledge source • Domain knowledge • Process • determine user’s requirements • apply domain knowledge to determine best item