{"id":"https://openalex.org/W2105831665","doi":"https://doi.org/10.1145/1367497.1367693","title":"Collaborative filtering on skewed datasets","display_name":"Collaborative filtering on skewed datasets","publication_year":2008,"publication_date":"2008-04-21","ids":{"openalex":"https://openalex.org/W2105831665","doi":"https://doi.org/10.1145/1367497.1367693","mag":"2105831665"},"language":"en","primary_location":{"id":"doi:10.1145/1367497.1367693","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074867889","display_name":"Somnath Banerjee","orcid":"https://orcid.org/0000-0002-4947-7649"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]},{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Somnath Banerjee","raw_affiliation_strings":["Hewlett-Packard Labs, Bangalore, India","Hewlett-Packard Laboratories, Bangalore, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Bangalore, India","institution_ids":["https://openalex.org/I4210117576"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080407571","display_name":"Krishnan Ramanathan","orcid":"https://orcid.org/0000-0001-9155-6351"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]},{"id":"https://openalex.org/I4210117576","display_name":"Hewlett-Packard (India)","ror":"https://ror.org/02ffkja82","country_code":"IN","type":"company","lineage":["https://openalex.org/I1324840837","https://openalex.org/I4210117576"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Krishnan Ramanathan","raw_affiliation_strings":["Hewlett-Packard Labs, Bangalore, India","Hewlett-Packard Laboratories, Bangalore, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Labs, Bangalore, India","institution_ids":["https://openalex.org/I4210117576"]},{"raw_affiliation_string":"Hewlett-Packard Laboratories, Bangalore, India#TAB#","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0143,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.75290583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1135","last_page":"1136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"Collaborative filtering","score":0.8484272956848145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7397025227546692},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.66314697265625},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5147050023078918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4714452028274536},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45883646607398987},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42765721678733826},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4180241823196411},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4178084135055542},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09908083081245422}],"concepts":[{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.8484272956848145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7397025227546692},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.66314697265625},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5147050023078918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4714452028274536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45883646607398987},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42765721678733826},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4180241823196411},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4178084135055542},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09908083081245422},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1367497.1367693","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1367497.1367693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.401.450","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.401.450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2008.org/papers/pdf/p1135-banerjeeA.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2049455633","https://openalex.org/W2069480896","https://openalex.org/W2123427850","https://openalex.org/W2171960770"],"related_works":["https://openalex.org/W1484355083","https://openalex.org/W2772628444","https://openalex.org/W4220714703","https://openalex.org/W2735929803","https://openalex.org/W2170391450","https://openalex.org/W2098758514","https://openalex.org/W3008845055","https://openalex.org/W2041004656","https://openalex.org/W135044020","https://openalex.org/W4376854386"],"abstract_inverted_index":{"Many":[0],"real":[1,49],"life":[2],"datasets":[3,28],"have":[4],"skewed":[5,27],"distributions":[6],"of":[7,12,31,77],"events":[8,15],"when":[9,70],"the":[10,18,29,32,65],"probability":[11],"observing":[13],"few":[14],"far":[16],"exceeds":[17],"others.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,71],"observed":[24],"that":[25],"in":[26],"state":[30],"art":[33],"collaborative":[34],"filtering":[35],"methods":[36],"perform":[37],"worse":[38],"than":[39],"a":[40,48,73,79,86],"simple":[41],"probabilistic":[42],"model.":[43],"Our":[44],"test":[45],"bench":[46],"includes":[47],"ad":[50],"click":[51],"stream":[52],"dataset":[53,69],"which":[54],"is":[55,61],"naturally":[56],"skewed.":[57],"The":[58],"same":[59],"conclusion":[60],"obtained":[62],"even":[63],"from":[64],"popular":[66],"movie":[67,87],"rating":[68,84],"pose":[72],"binary":[74],"prediction":[75],"problem":[76],"whether":[78],"user":[80],"will":[81],"give":[82],"maximum":[83],"to":[85],"or":[88],"not.":[89]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}