Editing Recommender system (section)

== Overview ==
Recommender systems usually make use of either or both [[collaborative filtering]] and content-based filtering, as well as other systems such as [[knowledge-based systems]]. Collaborative filtering approaches build a model from a user's past behavior (items previously purchased or selected and/or numerical ratings given to those items) as well as similar decisions made by other users. This model is then used to predict items (or ratings for items) that the user may have an interest in.<ref name="Recommender2010">{{ cite encyclopedia| first1=Prem |last1=Melville |first2= Vikas|last2= Sindhwani |entry-url=http://www.prem-melville.com/publications/recommender-systems-eml2010.pdf |entry=Recommender Systems|title= Encyclopedia of Machine Learning|date= 2010 | doi=10.1007/978-0-387-30164-8_705 | publisher= Springer | pages= 829–838 | isbn = 978-0-387-30164-8 | editor1=Claude Sammut |editor2= Geoffrey I. Webb }}</ref> Content-based filtering approaches utilize a series of discrete, pre-tagged characteristics of an item in order to recommend additional items with similar properties.<ref name="mooney99">{{cite conference |author1=R. J. Mooney  |author2=L. Roy  |name-list-style=amp |year = 1999 |title = Content-based book recommendation using learning for text categorization |conference = In Workshop Recom. Sys.: Algo. and Evaluation }}</ref>

The differences between collaborative and content-based filtering can be demonstrated by comparing two early music recommender systems, [[Last.fm]] and [[Pandora Radio]].
* Last.fm creates a "station" of recommended songs by observing what bands and individual tracks the user has listened to on a regular basis and comparing those against the listening behavior of other users. Last.fm will play tracks that do not appear in the user's library, but are often played by other users with similar interests. As this approach leverages the behavior of users, it is an example of a [[collaborative filtering]] technique.<ref>{{Cite journal |last=Haupt |first=Jon |date=2009-06-01 |title=Last.fm: People-Powered Online Radio |journal=Music Reference Services Quarterly |volume=12 |issue=1–2 |pages=23–24 |doi=10.1080/10588160902816702 |s2cid=161141937 |issn=1058-8167}}</ref>
* Pandora uses the properties of a song or artist (a subset of the 400 attributes provided by the [[Music Genome Project]]) to seed a "station" that plays music with similar properties. User feedback is used to refine the station's results, deemphasizing certain attributes when a user "dislikes" a particular song and emphasizing other attributes when a user "likes" a song. This is an example of a content-based approach.

Each type of system has its strengths and weaknesses. In the above example, Last.fm requires a large amount of information about a user to make accurate recommendations. This is an example of the [[Cold start (recommender systems)|cold start]] problem, and is common in collaborative filtering systems.<ref name=":3">{{Cite journal|last1=Chen |first1=Hung-Hsuan|last2=Chen| first2=Pu|date=2019-01-09|title=Differentiating Regularization Weights -- A Simple Mechanism to Alleviate Cold Start in Recommender Systems|journal=ACM Transactions on Knowledge Discovery from Data |volume=13|pages=1–22|language=EN|doi=10.1145/3285954|s2cid=59337456}}</ref><ref name="rubens2016">{{cite book
|last1=Rubens |first1=Neil
|last2= Elahi|first2=Mehdi
 |last3=Sugiyama|first3=Masashi|last4=Kaplan|first4=Dain|editor1-last=Ricci
 |editor1-first=Francesco
 |editor2-last=Rokach|editor2-first=Lior
 |editor3-last=Shapira |editor3-first=Bracha
 |title=Recommender Systems Handbook
 |date=2016
 |pages=809–846
|publisher=Springer US
 |isbn=978-1-4899-7637-6
 |edition=2
 |chapter=Active Learning in Recommender Systems
 |chapter-url = https://rd.springer.com/book/10.1007/978-1-4899-7637-6
|doi=10.1007/978-1-4899-7637-6_24
}}</ref><ref>{{cite journal |last1=Bobadilla |first1=J. |last2=Ortega |first2=F. |last3=Hernando |first3=A. |last4=Alcalá |first4=J. |date=2011 |title=Improving collaborative filtering recommender system results and performance using genetic algorithms |journal=Knowledge-Based Systems |volume=24 |issue=8 |pages=1310–1316 | doi=10.1016/j.knosys.2011.06.005}}</ref><ref name="elahi2016">
{{cite journal|last1= Elahi|first1=Mehdi
|last2= Ricci|first2=Francesco
|last3=Rubens|first3=Neil
|title=A survey of active learning in collaborative filtering recommender systems|journal=Computer Science Review
|volume=20
|pages=29–50
|url=https://bia.unibz.it/view/delivery/39UBZ_INST/12291577960001241/13291617600001241|doi=10.1016/j.cosrev.2016.05.002
|year=2016
}}
</ref><ref name="schein02">
{{cite conference |author1 = Andrew I. Schein |author2=Alexandrin Popescul |author3=Lyle H. Ungar |author3-link=Lyle Ungar |author4=David M. Pennock |year = 2002 |title = Methods and Metrics for Cold-Start Recommendations |conference = Proceedings of the 25th Annual International [[Association for Computing Machinery|ACM]] [[Special Interest Group on Information Retrieval|SIGIR]] Conference on Research and Development in Information Retrieval (SIGIR 2002) |url = https://archive.org/details/sigir2002proceed0000inte/page/253 |isbn = 1-58113-561-0 |publisher = [[Association for Computing Machinery|ACM]] |pages = [https://archive.org/details/sigir2002proceed0000inte/page/253 253–260] |access-date = 2008-02-02 }}
</ref><ref name="bi2017">{{cite journal|last1=Bi|first1=Xuan|last2=Qu|first2=Annie|last3=Wang|first3=Junhui|last4=Shen|first4=Xiaotong|year=2017|title=A group-specific recommender system.|url=https://figshare.com/articles/journal_contribution/A_Group-Specific_Recommender_System/3803748/1/files/5921967.pdf|journal=Journal of the American Statistical Association|volume=112|issue=519|pages=1344–1353|doi=10.1080/01621459.2016.1219261|s2cid=125187672}}</ref> Whereas Pandora needs very little information to start, it is far more limited in scope (for example, it can only make recommendations that are similar to the original seed).

Recommender systems are a useful alternative to [[search algorithm]]s since they help users discover items they might not have found otherwise. Of note, recommender systems are often implemented using search engines indexing non-traditional data.

Recommender systems have been the focus of several granted patents,<ref>Stack, Charles. "[https://patentimages.storage.googleapis.com/pdfs/US6782370.pdf System and method for providing recommendation of goods and services based on recorded purchasing history]." U.S. Patent 7,222,085, issued May 22, 2007.</ref><ref>Herz, Frederick SM. "Customized electronic newspapers and advertisements." U.S. Patent 7,483,871, issued January 27, 2009.
</ref><ref>
Herz, Frederick, Lyle Ungar, Jian Zhang, and David Wachob. "[https://patentimages.storage.googleapis.com/3c/1b/54/5c6688e454a63a/US8056100.pdf System and method for providing access to data using customer profiles]." U.S. Patent 8,056,100, issued November 8, 2011.
</ref><ref>
Harbick, Andrew V., Ryan J. Snodgrass, and Joel R. Spiegel. "[https://patents.google.com/patent/US8468046B2/en Playlist-based detection of similar digital works and work creators]." U.S. Patent 8,468,046, issued June 18, 2013.
</ref><ref>
Linden, Gregory D., Brent Russell Smith, and Nida K. Zada. "[https://patentimages.storage.googleapis.com/3c/f6/13/d5f70fcdcf1b6d/US9070156.pdf Automated detection and exposure of behavior-based relationships between browsable items]." U.S. Patent 9,070,156, issued June 30, 2015.</ref> and there are more than 50 software libraries<ref>{{Cite web |title=Recommender-System Software Libraries & APIs – RS_c |url=https://recommender-systems.com/resources/software-libraries/ |access-date=2024-11-18 |language=en-GB}}</ref> that support the development of recommender systems including LensKit,<ref>{{Cite book |last=Ekstrand |first=Michael |title=Computer Science Faculty Publications and Presentations |date=2018-08-21 |chapter=The LKPY Package for Recommender Systems Experiments |chapter-url=https://scholarworks.boisestate.edu/cs_facpubs/147/ |publisher=Boise State University, ScholarWorks |doi=10.18122/cs_facpubs/147/boisestate}}</ref><ref>{{Cite book |last1=Vente |first1=Tobias |last2=Ekstrand |first2=Michael |last3=Beel |first3=Joeran |chapter=Introducing LensKit-Auto, an Experimental Automated Recommender System (AutoRecSys) Toolkit |date=2023-09-14 |title=Proceedings of the 17th ACM Conference on Recommender Systems |chapter-url=https://dl.acm.org/doi/10.1145/3604915.3610656 |language=en |publisher=ACM |pages=1212–1216 |doi=10.1145/3604915.3610656 |isbn=979-8-4007-0241-9}}</ref> RecBole,<ref>{{Cite book |last1=Zhao |first1=Wayne Xin |last2=Mu |first2=Shanlei |last3=Hou |first3=Yupeng |last4=Lin |first4=Zihan |last5=Chen |first5=Yushuo |last6=Pan |first6=Xingyu |last7=Li |first7=Kaiyuan |last8=Lu |first8=Yujie |last9=Wang |first9=Hui |last10=Tian |first10=Changxin |last11=Min |first11=Yingqian |last12=Feng |first12=Zhichao |last13=Fan |first13=Xinyan |last14=Chen |first14=Xu |last15=Wang |first15=Pengfei |chapter=RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms |date=2021-10-26 |title=Proceedings of the 30th ACM International Conference on Information & Knowledge Management |chapter-url=https://dl.acm.org/doi/10.1145/3459637.3482016 |language=en |publisher=ACM |pages=4653–4664 |doi=10.1145/3459637.3482016 |arxiv=2011.01731 |isbn=978-1-4503-8446-9}}</ref> ReChorus<ref>{{Cite book |last1=Li |first1=Jiayu |last2=Li |first2=Hanyu |last3=He |first3=Zhiyu |last4=Ma |first4=Weizhi |last5=Sun |first5=Peijie |last6=Zhang |first6=Min |last7=Ma |first7=Shaoping |chapter=ReChorus2.0: A Modular and Task-Flexible Recommendation Library |date=2024-10-08 |title=18th ACM Conference on Recommender Systems |chapter-url=https://dl.acm.org/doi/10.1145/3640457.3688076 |language=en |publisher=ACM |pages=454–464 |doi=10.1145/3640457.3688076 |isbn=979-8-4007-0505-2}}</ref> and RecPack.<ref>{{Cite book |last1=Michiels |first1=Lien |last2=Verachtert |first2=Robin |last3=Goethals |first3=Bart |chapter=RecPack: An(other) Experimentation Toolkit for Top-N Recommendation using Implicit Feedback Data |date=2022-09-18 |title=Proceedings of the 16th ACM Conference on Recommender Systems |chapter-url=https://dl.acm.org/doi/10.1145/3523227.3551472 |language=en |publisher=ACM |pages=648–651 |doi=10.1145/3523227.3551472 |isbn=978-1-4503-9278-5}}</ref>