@article{burke_balanced_2018,
	title = {Balanced Neighborhoods for Multi-sided Fairness in Recommendation},
	volume = {81},
	url = {http://proceedings.mlr.press/v81/burke18a.html},
	abstract = {Fairness has emerged as an important category of analysis for machine
learning systems in some application areas. In extending the concept of
fairness to recommender systems, there is an essential tension between the
goals of fairness and those of personalization. However, there are
contexts in which equity across recommendation outcomes is a desirable
goal. It is also the case that in some applications fairness may be a
multisided concept, in which the impacts on multiple groups of individuals
must be considered. In this paper, we examine two different cases of
fairness-aware recommender systems: consumer-centered and
provider-centered. We explore the concept of a balanced neighborhood as a
mechanism to preserve personalization in recommendation while enhancing
the fairness of recommendation outcomes. We show that a modified version
of the Sparse Linear Method ({SLIM}) can be used to improve the balance of
user and item neighborhoods, with the result of achieving greater outcome
fairness in real-world datasets with minimal loss in ranking performance.},
	pages = {202--214},
	author = {Burke, Robin and Sonboli, Nasim and Ordonez-Gauger, Aldo},
	date = {2018}
}

{"_id":"WxTWKfGJatsWjRk4Z","bibbaseid":"burke-sonboli-ordonezgauger-balancedneighborhoodsformultisidedfairnessinrecommendation","authorIDs":[],"author_short":["Burke, R.","Sonboli, N.","Ordonez-Gauger, A."],"bibdata":{"bibtype":"article","type":"article","title":"Balanced Neighborhoods for Multi-sided Fairness in Recommendation","volume":"81","url":"http://proceedings.mlr.press/v81/burke18a.html","abstract":"Fairness has emerged as an important category of analysis for machine learning systems in some application areas. In extending the concept of fairness to recommender systems, there is an essential tension between the goals of fairness and those of personalization. However, there are contexts in which equity across recommendation outcomes is a desirable goal. It is also the case that in some applications fairness may be a multisided concept, in which the impacts on multiple groups of individuals must be considered. In this paper, we examine two different cases of fairness-aware recommender systems: consumer-centered and provider-centered. We explore the concept of a balanced neighborhood as a mechanism to preserve personalization in recommendation while enhancing the fairness of recommendation outcomes. We show that a modified version of the Sparse Linear Method (SLIM) can be used to improve the balance of user and item neighborhoods, with the result of achieving greater outcome fairness in real-world datasets with minimal loss in ranking performance.","pages":"202–214","author":[{"propositions":[],"lastnames":["Burke"],"firstnames":["Robin"],"suffixes":[]},{"propositions":[],"lastnames":["Sonboli"],"firstnames":["Nasim"],"suffixes":[]},{"propositions":[],"lastnames":["Ordonez-Gauger"],"firstnames":["Aldo"],"suffixes":[]}],"date":"2018","bibtex":"@article{burke_balanced_2018,\n\ttitle = {Balanced Neighborhoods for Multi-sided Fairness in Recommendation},\n\tvolume = {81},\n\turl = {http://proceedings.mlr.press/v81/burke18a.html},\n\tabstract = {Fairness has emerged as an important category of analysis for machine\nlearning systems in some application areas. In extending the concept of\nfairness to recommender systems, there is an essential tension between the\ngoals of fairness and those of personalization. However, there are\ncontexts in which equity across recommendation outcomes is a desirable\ngoal. It is also the case that in some applications fairness may be a\nmultisided concept, in which the impacts on multiple groups of individuals\nmust be considered. In this paper, we examine two different cases of\nfairness-aware recommender systems: consumer-centered and\nprovider-centered. We explore the concept of a balanced neighborhood as a\nmechanism to preserve personalization in recommendation while enhancing\nthe fairness of recommendation outcomes. We show that a modified version\nof the Sparse Linear Method ({SLIM}) can be used to improve the balance of\nuser and item neighborhoods, with the result of achieving greater outcome\nfairness in real-world datasets with minimal loss in ranking performance.},\n\tpages = {202--214},\n\tauthor = {Burke, Robin and Sonboli, Nasim and Ordonez-Gauger, Aldo},\n\tdate = {2018}\n}\n\n","author_short":["Burke, R.","Sonboli, N.","Ordonez-Gauger, A."],"key":"burke_balanced_2018","id":"burke_balanced_2018","bibbaseid":"burke-sonboli-ordonezgauger-balancedneighborhoodsformultisidedfairnessinrecommendation","role":"author","urls":{"Paper":"http://proceedings.mlr.press/v81/burke18a.html"},"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://fair-ia.ekstrandom.net/fair-ia.bib","creationDate":"2020-04-09T18:53:45.727Z","downloads":0,"keywords":[],"search_terms":["balanced","neighborhoods","multi","sided","fairness","recommendation","burke","sonboli","ordonez-gauger"],"title":"Balanced Neighborhoods for Multi-sided Fairness in Recommendation","year":null,"dataSources":["FRCCaPECNMucjb6Hk"]}