@inproceedings{ekstrand_when_2012,
	address = {New York, NY, USA},
	title = {When recommenders fail: predicting recommender failure for algorithm selection and combination},
	url = {http://doi.acm.org/10.1145/2365952.2366002},
	doi = {10.1145/2365952.2366002},
	abstract = {Hybrid recommender systems --- systems using multiple algorithms together
to improve recommendation quality --- have been well-known for many years
and have shown good performance in recent demonstrations such as the
NetFlix Prize. Modern hybridization techniques, such as feature-weighted
linear stacking, take advantage of the hypothesis that the relative
performance of recommenders varies by circumstance and attempt to optimize
each item score to maximize the strengths of the component recommenders.
Less attention, however, has been paid to understanding what these
strengths and failure modes are. Understanding what causes particular
recommenders to fail will facilitate better selection of the component
recommenders for future hybrid systems and a better understanding of how
individual recommender personalities can be harnessed to improve the
recommender user experience. We present an analysis of the predictions
made by several well-known recommender algorithms on the MovieLens 10M
data set, showing that for many cases in which one algorithm fails, there
is another that will correctly predict the rating.},
	urldate = {2012-12-13},
	booktitle = {{RecSys} '12},
	publisher = {ACM},
	author = {Ekstrand, Michael D and Riedl, John T},
	year = {2012},
	note = {Journal Abbreviation: RecSys '12},
	pages = {233--236},
}

{"_id":"XdRBz3JBggx6ms65w","bibbaseid":"ekstrand-riedl-whenrecommendersfailpredictingrecommenderfailureforalgorithmselectionandcombination-2012","authorIDs":[],"author_short":["Ekstrand, M. D","Riedl, J. T"],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"New York, NY, USA","title":"When recommenders fail: predicting recommender failure for algorithm selection and combination","url":"http://doi.acm.org/10.1145/2365952.2366002","doi":"10.1145/2365952.2366002","abstract":"Hybrid recommender systems — systems using multiple algorithms together to improve recommendation quality — have been well-known for many years and have shown good performance in recent demonstrations such as the NetFlix Prize. Modern hybridization techniques, such as feature-weighted linear stacking, take advantage of the hypothesis that the relative performance of recommenders varies by circumstance and attempt to optimize each item score to maximize the strengths of the component recommenders. Less attention, however, has been paid to understanding what these strengths and failure modes are. Understanding what causes particular recommenders to fail will facilitate better selection of the component recommenders for future hybrid systems and a better understanding of how individual recommender personalities can be harnessed to improve the recommender user experience. We present an analysis of the predictions made by several well-known recommender algorithms on the MovieLens 10M data set, showing that for many cases in which one algorithm fails, there is another that will correctly predict the rating.","urldate":"2012-12-13","booktitle":"RecSys '12","publisher":"ACM","author":[{"propositions":[],"lastnames":["Ekstrand"],"firstnames":["Michael","D"],"suffixes":[]},{"propositions":[],"lastnames":["Riedl"],"firstnames":["John","T"],"suffixes":[]}],"year":"2012","note":"Journal Abbreviation: RecSys '12","pages":"233–236","bibtex":"@inproceedings{ekstrand_when_2012,\n\taddress = {New York, NY, USA},\n\ttitle = {When recommenders fail: predicting recommender failure for algorithm selection and combination},\n\turl = {http://doi.acm.org/10.1145/2365952.2366002},\n\tdoi = {10.1145/2365952.2366002},\n\tabstract = {Hybrid recommender systems --- systems using multiple algorithms together\nto improve recommendation quality --- have been well-known for many years\nand have shown good performance in recent demonstrations such as the\nNetFlix Prize. Modern hybridization techniques, such as feature-weighted\nlinear stacking, take advantage of the hypothesis that the relative\nperformance of recommenders varies by circumstance and attempt to optimize\neach item score to maximize the strengths of the component recommenders.\nLess attention, however, has been paid to understanding what these\nstrengths and failure modes are. Understanding what causes particular\nrecommenders to fail will facilitate better selection of the component\nrecommenders for future hybrid systems and a better understanding of how\nindividual recommender personalities can be harnessed to improve the\nrecommender user experience. We present an analysis of the predictions\nmade by several well-known recommender algorithms on the MovieLens 10M\ndata set, showing that for many cases in which one algorithm fails, there\nis another that will correctly predict the rating.},\n\turldate = {2012-12-13},\n\tbooktitle = {{RecSys} '12},\n\tpublisher = {ACM},\n\tauthor = {Ekstrand, Michael D and Riedl, John T},\n\tyear = {2012},\n\tnote = {Journal Abbreviation: RecSys '12},\n\tpages = {233--236},\n}\n\n","author_short":["Ekstrand, M. D","Riedl, J. T"],"key":"ekstrand_when_2012","id":"ekstrand_when_2012","bibbaseid":"ekstrand-riedl-whenrecommendersfailpredictingrecommenderfailureforalgorithmselectionandcombination-2012","role":"author","urls":{"Paper":"http://doi.acm.org/10.1145/2365952.2366002"},"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://api.zotero.org/users/6655/collections/TJPPJ92X/items?key=VFvZhZXIoHNBbzoLZ1IM2zgf&format=bibtex&limit=100","creationDate":"2020-03-27T02:34:35.369Z","downloads":0,"keywords":[],"search_terms":["recommenders","fail","predicting","recommender","failure","algorithm","selection","combination","ekstrand","riedl"],"title":"When recommenders fail: predicting recommender failure for algorithm selection and combination","year":2012,"dataSources":["5Dp4QphkvpvNA33zi","jfoasiDDpStqkkoZB","BiuuFc45aHCgJqDLY"]}