推薦系統(tǒng)設(shè)計(jì).ppt

1、Design Strategies for Recommender Systems,Rashmi Sinha Jan 2006, UIE Web App Summit,UIE Web App Summit,2,What are Recommender Systems?,Circa 2001 Systems that attempt to predict items, e.g., movies, music, books, that a user may be interested in (given some information about the users profile) e.g.,

2、 Amazon people who liked this book also liked, Netflix recommendations Circa 2006 Systems that help people find information that will interest them, by facilitating social / conceptual connections or other means Pandora, Last.fm,UIE Web App Summit,3,Designing different finding experiences,Some exper

3、iences guide user, others just point in a general direction Desired experience depends on user task, time constraints, mood etc.,Theres more than one way to get from here to there,UIE Web App Summit,4,User experience in search/browse interfaces,More controlled experience Every movement (forward, mak

4、ing a turn) is a conscious choice System should provide information at every step If user takes wrong turn, go back a step or two / start again,Like driving a car,UIE Web App Summit,5,User Experience with Recommender Systems,User has less control over specifics of interaction System does not provide

5、 information about specifics of action More of a “black box” model (some input from user, output from systems),Like riding a roller coaster,Recommender Systems Circa 2001,UIE Web App Summit,7,what movies you should watch (Reel, RatingZone, Amazon) what music you should listen to (CDNow, Mubu, Gigabe

6、at) what websites you should visit (Alexa) what jokes you will like (Jester) where to go on vacation (TripleHop) sense that others are out there User profiles and photos put a human face on the system interactions,Spotback,UIE Web App Summit,37,What people are doing on Digg,UIE Web App Summit,38,Des

7、ign Principle 4: Instant gratification,Provide personalized recommendations as soon as a user provides some input Pandora: one song instant radio station Spotback: one article rating instant articles of interest Note: need lots of user data for this to work well (cold start problem emerges again?),U

8、IE Web App Summit,39,Design Principle 5: Cultivate user independence,Prevent mobs, optimize the “wisdom of crowds”,UIE Web App Summit,40,Cultivating wise crowds,Four conditions Cognitive Diversity Independence Decentralization Easy Aggregation,UIE Web App Summit,41,Design Principle 6: Provide access

9、 to long tail, keep content fast moving,Make “l(fā)ong tail” accessible Recommend lots of different stuff (not just most popular) Top 100 lists Keeps recs from getting stale Use time as a dimension in system design Enable fast movement. Rise to top. Get displaced. e.g., “whats fresh today” e.g., Slidesh

10、are popularity model,UIE Web App Summit,42,Design Principle 7: Expose metadata, make it linkable,Exposing tags and user lists Enable “pivot browsing” Every piece of content should have a unique, easily guessed URL.,UIE Web App Summit,43,Design Principle 8: Provide balance between public methods for adjusting this setting,UIE Web App Summit,46,Things to try at home!,Create an account on Read Emergence, Wisdom of Crowds Play a Multiplayer Online Game (WOW, Second Life) Pla