{"id":"https://openalex.org/W2150782899","doi":"https://doi.org/10.1145/1390156.1390250","title":"On the chance accuracies of large collections of classifiers","display_name":"On the chance accuracies of large collections of classifiers","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2150782899","doi":"https://doi.org/10.1145/1390156.1390250","mag":"2150782899"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390250","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","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/A5050776972","display_name":"Mark Palatucci","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Palatucci","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101513166","display_name":"J. Andrew Carlson","orcid":"https://orcid.org/0000-0002-6866-6314"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Carlson","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.3075,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.91064871,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"744","last_page":"751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.944100022315979,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7003072500228882},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.688811719417572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6251192092895508},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6104174256324768},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.579839825630188},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5676829218864441},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5057268142700195},{"id":"https://openalex.org/keywords/false-discovery-rate","display_name":"False discovery rate","score":0.49360501766204834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42493486404418945},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36422353982925415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7003072500228882},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.688811719417572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6251192092895508},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6104174256324768},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.579839825630188},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5676829218864441},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5057268142700195},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.49360501766204834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42493486404418945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36422353982925415},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1390156.1390250","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.6285","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.6285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icml2008.cs.helsinki.fi/papers/323.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.4103","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.4103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ri.cmu.edu/pub_files/pub4/palatucci_mark_2008_1/palatucci_mark_2008_1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1498800329","https://openalex.org/W1509822087","https://openalex.org/W1974534365","https://openalex.org/W2059495650","https://openalex.org/W2087684630","https://openalex.org/W2110065044","https://openalex.org/W2112532472","https://openalex.org/W2135046866","https://openalex.org/W2496945004","https://openalex.org/W2751862591","https://openalex.org/W2799002609","https://openalex.org/W3118259273","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2389124870","https://openalex.org/W1921844237","https://openalex.org/W4388745254","https://openalex.org/W2889302474","https://openalex.org/W2980082554","https://openalex.org/W2767419625","https://openalex.org/W2389704471","https://openalex.org/W1517228774","https://openalex.org/W2734997742","https://openalex.org/W2117019857"],"abstract_inverted_index":{"We":[0,14,42,57,81],"provide":[1,47],"a":[2,35,48],"theoretical":[3],"analysis":[4],"of":[5,9,12,22],"the":[6,74,86,99],"chance":[7],"accuracies":[8],"large":[10],"collections":[11],"classifiers.":[13],"show":[15,67,83],"that":[16,68,84],"on":[17,61,85],"problems":[18],"with":[19],"small":[20],"numbers":[21],"examples,":[23],"some":[24],"classifier":[25],"can":[26],"perform":[27],"well":[28],"by":[29],"random":[30],"chance,":[31],"and":[32,63,66],"we":[33],"derive":[34],"theorem":[36,45],"to":[37,46,73],"explicitly":[38],"calculate":[39],"this":[40,44,59,89],"accuracy.":[41],"use":[43],"principled":[49],"feature":[50],"selection":[51],"criterion":[52],"for":[53],"sparse,":[54],"high-dimensional":[55],"problems.":[56],"evaluate":[58],"method":[60],"microarray":[62],"fMRI":[64,87],"datasets":[65],"it":[69],"performs":[70],"very":[71],"close":[72],"optimal":[75],"accuracy":[76],"obtained":[77],"from":[78],"an":[79],"oracle.":[80],"also":[82],"dataset":[88],"technique":[90],"chooses":[91],"relevant":[92],"features":[93],"successfully":[94],"while":[95],"another":[96],"state-of-the-art":[97],"method,":[98],"False":[100],"Discovery":[101],"Rate":[102],"(FDR),":[103],"completely":[104],"fails":[105],"at":[106],"standard":[107],"significance":[108],"levels.":[109]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}