Recommender system

Recommender systems form a specific type of information filtering (IF) technique that attempts to present information items (movies, music, books, news, images, web pages) that are likely of interest to the user. Typically, a recommender system compares the user's profile to some reference characteristics. These characteristics may be from the information item (the content-based approach) or the user's social environment (the collaborative filtering approach).

Overview

When building the user's profile a distinction is made between explicit and implicit forms of data collection.

Examples of explicit data collection include the following:

*Asking a user to rate an item on a sliding scale.
*Asking a user to rank a collection of items from favorite to least favorite.
*Presenting two items to a user and asking him/her to choose the best one.
*Asking a user to create a list of items that he/she likes.

Examples of implicit data collection include the following:
*Observing the items that a user views in an online store.
*Analyzing item/user viewing times [citation |last=Parsons |first=J. |last2=Ralph |first2=P. |last3=Gallagher |first3=K. |date=July 2004 |month=July |year=2004 |title=Using viewing time to infer user preference in recommender systems. |publisher=AAAI Workshop in Semantic Web Personalization, San Jose, California.]
*Keeping a record of the items that a user purchases online.
*Obtaining a list of items that a user has listened to or watched on his/her computer.
*Analyzing the user's social network and discovering similar likes and dislikes

The recommender system compares the collected data to similar data collected from others and calculates a list of recommended items for the user. Several commercial and non-commercial examples are listed in the article on collaborative filtering systems.Adomavicius provides an overview of recommender systems. [citation |last=Adomavicius |first=G. |last2=Tuzhilin |first2=A. |url=http://portal.acm.org/citation.cfm?id=1070611.1070751 |title=Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions |journal=IEEE Transactions on Knowledge and Data Engineering |volume=17 |issue=6 |date=June 2005 |month=June |year=2005 |pages=734–749 |doi=10.1109/TKDE.2005.99 |issn=1041-4347.] Herlocker provides an overview of evaluation techniques for recommender systems. [citation |last=Herlocker |first=J. L. |last2=Konstan |first2=J. A. |last3=Terveen |first3=L. G. |last4=Riedl |first4=J. T. |date=January 2004 |month=January |year=2004 |url=http://portal.acm.org/citation.cfm?id=963772 |title=Evaluating collaborative filtering recommender systems |journal=ACM Trans. Inf. Syst. |volume=22 |issue=1 |pages=5–53 |doi=10.1145/963770.963772 |issn=1046-8188.]

More recently, a successful recommender system has been introduced for bricks and mortar superstores based upon statistical inference [Quatse, Jesse and Najmi, Amir (2007) "Empirical Bayesian Targeting," Proceedings, WORLDCOMP'07, World Congress in Computer Science, Computer Engineering, and Applied Computing.] as opposed to the Collaborative Filtering techniques of eCommerce. Redemption rates, or "hit rates," are much higher averaging as much as 45% in chain grocery stores.

Recommender systems are a useful alternative to search algorithms since they help users discover items they might not have found by themselves. Interestingly enough, recommender systems are often implemented using search engines indexing non-traditional data.

Recommender systems are also sometimes known colloquially as "Gilligans".

Algorithms

One of the most commonly used algorithms in recommender systems is Nearest Neighborhood approach. [citation |last=Sarwar |first=B. |last2=Karypis |first2=G. |last3=Konstan |first3=J. |last4=Riedl |first4=J. |year=2000 |url=http://glaros.dtc.umn.edu/gkhome/node/122 |title=Application of Dimensionality Reduction in Recommender System A Case Study.] . In a social network, a particular user's neighborhood with similar taste or interest can be found by calculating Pearson Correlation, by collecting the preference data of top-N nearest neighbors of the particular user, the user's preference can be predicted by calculating the data using certain techniques.

Examples

* [http://www.aggregateknowledge.com/ Aggregate Knowledge] (recommendations and discovery)
* Baynote (recommendation web service)
* [http://www.choicestream.com ChoiceStream] (recommendation service provider)
* [http://www.clicktorch.com Clicktorch] Intelligent Product and Content Recommendation System
* Collarity (media recommendation platform)
* [http://www.configworks.com ConfigWorks] (interactive selling solutions)
* [http://www.criteo.com/ Criteo] (recommendation technology)
* [http://www.criticker.com/ Criticker] (film recommendation engine)
* Daily Me (news recommendation system (hypothetical))
* [http://foodio54.com Foodio54] (restaurant recommender service)
* [http://www.freshnotes.com/ FreshNotes] (recommendation engine)
* [http://www.heeii.com Heeii] (recommendation plugin)
* [http://www.igodigital.com/ iGoDigital] (recommendation engine)
* inSuggest (recommendation engine)
* iLike (music service)
* Last.fm (music service)
* [http://loomia.com/ Loomia] (Social and Personalized Recommendations For Media, Content and Retail Sites)
* MeeMix (personalized music service)
* [http://business.mufin.com mufin] (provider of semantic audio recommendation technologies)
* MyStrands (developer of social recommendation technologies)
* Pandora (music service)
* [http://www.photoree.com Photoree] (image recommender system)
* [http://www.prudsys.com/Software/Komponenten/RecommendationEngine/ prudsys RE] (recommendation system)
* Slacker (music service)
* StumbleUpon (web discovery service)
* StyleFeeder (personalized shopping search)
* [http://www.tastehood.com/ Tastehood] (recommendation engine for movies, music, books and more)
* [http://www.tastekid.com/ Taste Kid] (music, films and books recommendation engine)
* [http://www.tastevine.com/ TasteVine] (wine)
* Zemanta (authoring-time suggestions service)
* [http://www.imhonet.ru/ IMHONET] (1st russian language recommendation service)

ee also

* Cold start
* Collaborative filtering
* Collective intelligence
* Personalized marketing
* Preference elicitation
* Product Finders
* The Long Tail

References

External links

* [http://www.clicktorch.com Clicktorch] Intelligent Product and Content Recommendation System)
* [http://www.photoree.com Photoree] (image recommendation system)
* [http://www.commendo.at commendo] (large scale recommender systems)
* [http://www.prudsys.com/Software/Komponenten/RecommendationEngine/1204804625/ prudsys] (recommender systems based on reinforcement learning technologies)
* [http://like-i-like.org Like-I-Like.org] (movie recommendation web service)
* [http://scripts.mit.edu/~cci/wiki/index.php?title=Computer_supported_collaborative_work_perspective_on_collective_intelligence MIT-CCI wiki on "Computer supported collaborative work perspective on collective intelligence"]
* [http://www.andreas-ittner.de/index_rs.html Collection of research papers]
* [http://search.barnesandnoble.com/booksearch/isbnInquiry.asp?z=y&EAN=9780446530033&itm=1 Word of Mouth: The Marketing Power of Collaborative Filtering]
* [http://www.cs.utexas.edu/users/ml/publication/paper.cgi?paper=cbcf-aaai-02.ps.gz Content-Boosted Collaborative Filtering for Improved Recommendations. Prem Melville, Raymond J. Mooney, and Ramadass Nagarajan]
*
* [http://www.deitel.com/ResourceCenters/Web20/RecommenderSystems/RecommenderSystemsandCollaborativeFiltering/tabid/1318/Default.aspx Recommended Systems Resource Center]
* [http://www.localina.com Localina (location recommendation system)]
* [http://www.aggregateknowledge.com/des_riedl.html Interview: Recommendations 2.0 by John Riedl, Ph.D.]
* [http://www.andreas-ittner.de/recommender-literatur/17-quellen-recommender-systeme/10-quellen-recommender-systeme.html Web's largest collection of scientific literatur about recommender systems]
* [http://www.media-choice.com MediaChoice] (Patented Recommendation System)

Research Groups

* [http://www.grouplens.org/ GroupLens]
* [http://dbis.informatik.uni-freiburg.de/index.php?project=2nd-Gen-RS IFI DBIS Next Generation Recommender Systems]
* [http://www.em.uni-karlsruhe.de/research/projects/reckvk/index.php?language=en&id=Summary IISM]
* [http://users.ecs.soton.ac.uk/sem99r/publications.html Univ. of Southampton IAM Group]
* [http://eecs.oregonstate.edu/iis/CoFE/ CoFE]
* [http://www.telin.nl/index.cfm?project=Duine&language=en Duine]
* [http://www.cs.utexas.edu/users/mooney/libra/ LIBRA]
* [http://www.uni-klu.ac.at/tewi/inf/ainf/isbi/index.html Intelligent Systems and Business Informatics research group at University Klagenfurt, Austria]
* [http://en.wikipedia.org/wiki/Netflix_prize Netflix prize]
* [http://www.unifr.ch/econophysics/ Univ. of Fribourg Statistical Physics Group]

[http://recsys.acm.org/ ACM Recommender Systems Series]

* [http://recsys.acm.org/ RecSys 2008]
* RecSys 2007: [http://recsys.acm.org/2007/ home page] , [http://portal.acm.org/toc.cfm?id=1297231&type=proceeding&coll=ACM&dl=ACM&CFID=5530539&CFTOKEN=21609831 proceedings]
* [http://www.mystrands.com/corp/summerschool06.vm Recommenders06: Summer School on The Present and Future of Recommender Systems]

Journal Special Issues

* [http://tweb.acm.org/RecSysSpecialIssue.html ACM Transactions on the Web Special issue on Recommenders on the Web]
* [http://www.configworks.com/AICOM/ AI Communications Special issue on Recommender Systems: call for papers]
* [http://csdl2.computer.org/persagen/DLAbsToc.jsp?resourcePath=/dl/mags/ex/&toc=comp/mags/ex/2007/03/x3toc.xml IEEE Intelligent Systems Special Issue on Recommender Systems, Vol. 22(3), 2007]
* [http://portal.acm.org/toc.cfm?id=1278152 International Journal of Electronic Commerce Special Issue on Recommender Systems, Volume 11, Number 2 (Winter 2006-07)]
* [http://portal.acm.org/citation.cfm?id=1096737.1096738 ACM Transactions on Computer-Human Interaction (TOCHI) Special Section on Recommender Systems Volume 12, Issue 3 (September 2005)]
* [http://portal.acm.org/toc.cfm?id=963770 ACM Transactions on Information Systems (TOIS) Special Issue on Recommender Systems, Volume 22, Issue 1 (January 2004)]
* [http://tourism.wu-wien.ac.at/Jitt/ Journal of Information Technology and Tourism Special issue on Recommender Systems, Volume 6, Number 3 (2003)]
* [http://portal.acm.org/citation.cfm?id=245121 Communications of the ACM Special issue on Recommender Systems, Volume 40, Issue 3 (March 1997)]

Workshops

* [http://www.wprrs08.fit.qut.edu.au/ WI'08 Workshop on Web Personalization, Reputation and Recommender Systems]
* [http://www.dirf.org/diwt2008/workshop2.asp ICADIWT 2008 - First International Workshop on Recommender Systems and Personalized Retrieval]
* [http://proserver3-iwas.uni-klu.ac.at/ECAI08-Recommender-Workshop/ ECAI'08 - Workshop on Recommender Systems]
* [http://kater.uni-koblenz.de/~openconf/recoll.2008/ ReColl'08 - International Workshop on Recommendation and Collaboration]
* [http://forwarding-iwas.uni-klu.ac.at/AAAI07-WS-Recommender-Systems/ AAAI'07 Workshop on Recommender Systems in e-Commerce]
* [http://www.wprs07.fit.qut.edu.au/ WI'07 Workshop on Web Personalization and Recommender Systems]
* [http://proserver3-iwas.uni-klu.ac.at/ECAI06-Recommender-Workshop/ ECAI 2006 Workshop on Recommender Systems]
* [http://web.engr.oregonstate.edu/~herlock/rsw2001/ ACM SIGIR 2001 Workshop on Recommender Systems]
* [http://www.cs.umbc.edu/~ian/sigir99-rec/ ACM SIGIR '99 Workshop on Recommender Systems]
* [http://www.patrickbaudisch.com/interactingwithrecommendersystems/ CHI' 99 Workshop Interacting with Recommender Systems ]

Further reading

*Hangartner, Rick, [http://www.msearchgroove.com/2007/12/17/guest-column-what-is-the-recommender-industry/ "What is the Recommender Industry?"] , MSearchGroove, December 17, 2007.