{"id":"https://openalex.org/W2163757302","doi":"https://doi.org/10.1145/1014052.1014063","title":"Data mining in metric space","display_name":"Data mining in metric space","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2163757302","doi":"https://doi.org/10.1145/1014052.1014063","mag":"2163757302"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014063","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"article","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/A5083893060","display_name":"Rich Caruana","orcid":"https://orcid.org/0000-0002-6383-7786"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rich Caruana","raw_affiliation_strings":["Cornell University"],"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029480393","display_name":"Alexandru Niculescu-Mizil","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandru Niculescu-Mizil","raw_affiliation_strings":["Cornell University"],"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083893060"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":13.4912,"has_fulltext":false,"cited_by_count":299,"citation_normalized_percentile":{"value":0.98782899,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"69","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9969000220298767,"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":0.9832000136375427,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9589999914169312,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/support-vector-machine","display_name":"Support vector machine","score":0.5757163763046265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.570160984992981},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5615496635437012},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5447360873222351},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.49618202447891235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49265986680984497},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47535985708236694},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4534851908683777},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.4502493739128113},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4373367428779602},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4337160587310791},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4127582907676697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4044707119464874},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3899151384830475},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3811606466770172},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35010063648223877},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3403622806072235}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5757163763046265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.570160984992981},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5615496635437012},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5447360873222351},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.49618202447891235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49265986680984497},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47535985708236694},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4534851908683777},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.4502493739128113},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4373367428779602},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4337160587310791},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4127582907676697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4044707119464874},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3899151384830475},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3811606466770172},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35010063648223877},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3403622806072235},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1014052.1014063","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332377","display_name":"Goddard Space Flight Center","ror":"https://ror.org/0171mag52"},{"id":"https://openalex.org/F4320338381","display_name":"SLAC National Accelerator Laboratory","ror":"https://ror.org/05gzmn429"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1509515766","https://openalex.org/W1549656520","https://openalex.org/W1576520375","https://openalex.org/W1599263113","https://openalex.org/W1618905105","https://openalex.org/W1985995090","https://openalex.org/W2084812512","https://openalex.org/W2143017915","https://openalex.org/W2170913656","https://openalex.org/W2756666283","https://openalex.org/W4312960235","https://openalex.org/W6634442568","https://openalex.org/W6635733909","https://openalex.org/W6671611538"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W4231274751","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2571255492","https://openalex.org/W4239293476"],"abstract_inverted_index":{"Many":[0],"criteria":[1,13,26,292],"can":[2],"be":[3],"used":[4],"to":[5,27,56,92,189,287],"evaluate":[6],"the":[7,104,163,167,229],"performance":[8,97,208,234],"of":[9,77,153,166],"supervised":[10],"learning.":[11],"Different":[12],"are":[14,54,135,139,293],"appropriate":[15,136],"in":[16,150],"different":[17],"settings,":[18],"and":[19,52,86,89,116,147,176,193,203,242,256,263,272],"it":[20,280],"is":[21,32,269,281],"not":[22,43,225,294],"always":[23],"clear":[24],"which":[25],"use.":[28],"A":[29],"further":[30],"complication":[31],"that":[33,36,123,134,160,184,228,251,267,279],"learning":[34,78],"methods":[35,79,199,231],"perform":[37,44,214],"well":[38,45,274],"on":[39,46,162,186,209,216,235],"one":[40,151,260],"criterion":[41],"may":[42],"other":[47,276],"criteria.":[48],"For":[49],"example,":[50],"SVMs":[51,202],"boosting":[53],"designed":[55],"optimize":[57,63],"accuracy,":[58,212,255],"whereas":[59],"neural":[60,81],"nets":[61],"typically":[62],"squared":[64,143,221,253],"error":[65],"or":[66],"cross":[67,145],"entropy.":[68],"We":[69,245],"conducted":[70],"an":[71],"empirical":[72],"study":[73],"using":[74],"a":[75,127,190,247,282],"variety":[76],"(SVMs,":[80],"nets,":[82],"k-nearest":[83],"neighbor,":[84],"bagged":[85],"boosted":[87,90,204],"trees,":[88],"stumps)":[91],"compare":[93],"nine":[94],"boolean":[95],"classification":[96],"metrics:":[98],"Accuracy,":[99],"Lift,":[100],"F-Score,":[101],"Area":[102],"under":[103],"ROC":[105,170,240,257],"Curve,":[106],"Average":[107],"Precision,":[108],"Precision/Recall":[109],"Break-Even":[110],"Point,":[111],"Squared":[112],"Error,":[113],"Cross":[114],"Entropy,":[115],"Probability":[117],"Calibration.":[118],"Multidimensional":[119],"scaling":[120],"(MDS)":[121],"shows":[122,266],"these":[124],"metrics":[125,133,159,183,210,218,237],"span":[126],"low":[128],"dimensional":[129],"manifold.":[130],"The":[131],"three":[132],"when":[137,289],"predictions":[138,188],"interpreted":[140],"as":[141,201,220,239],"probabilities:":[142],"error,":[144,254],"entropy,":[146],"calibration,":[148],"lay":[149],"part":[152],"metric":[154,286],"space":[155],"far":[156],"away":[157],"from":[158],"depend":[161,185],"relative":[164],"order":[165],"predicted":[168],"values:":[169],"area,":[171],"average":[172,243],"precision,":[173],"break-even":[174],"point,":[175],"lift.":[177],"In":[178],"between":[179],"them":[180],"fall":[181],"two":[182],"comparing":[187],"threshold:":[191],"accuracy":[192],"F-score.":[194],"As":[195],"expected,":[196],"maximum":[197],"margin":[198,230],"such":[200,219,238],"trees":[205],"have":[206,232],"excellent":[207,233],"like":[211],"but":[213],"poorly":[215],"probability":[217],"error.":[222],"What":[223],"was":[224,227],"expected":[226],"ordering":[236],"area":[241,258],"precision.":[244],"introduce":[246],"new":[248],"metric,":[249],"SAR,":[250],"combines":[252],"into":[259],"metric.":[261],"MDS":[262],"correlation":[264],"analysis":[265],"SAR":[268],"centrally":[270],"located":[271],"correlates":[273],"with":[275],"metrics,":[277],"suggesting":[278],"good":[283],"general":[284],"purpose":[285],"use":[288],"more":[290],"specific":[291],"known.":[295]},"counts_by_year":[{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":18},{"year":2012,"cited_by_count":23}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}