{"id":"https://openalex.org/W1989127053","doi":"https://doi.org/10.1145/1014052.1016916","title":"A general approach to incorporate data quality matrices into data mining algorithms","display_name":"A general approach to incorporate data quality matrices into data mining algorithms","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W1989127053","doi":"https://doi.org/10.1145/1014052.1016916","mag":"1989127053"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1016916","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1016916","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/A5030289182","display_name":"Ian Davidson","orcid":"https://orcid.org/0000-0002-1258-4213"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ian Davidson","raw_affiliation_strings":["SUNY Albany, Albany, NY","SUNY-Albany, Albany, NY"],"affiliations":[{"raw_affiliation_string":"SUNY Albany, Albany, NY","institution_ids":["https://openalex.org/I392282"]},{"raw_affiliation_string":"SUNY-Albany, Albany, NY","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103412695","display_name":"Ashish Grover","orcid":null},"institutions":[{"id":"https://openalex.org/I1332737386","display_name":"General Electric (United States)","ror":"https://ror.org/013msgt25","country_code":"US","type":"company","lineage":["https://openalex.org/I1332737386"]},{"id":"https://openalex.org/I4210134512","display_name":"GE Global Research (United States)","ror":"https://ror.org/03e06qt98","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134512"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashish Grover","raw_affiliation_strings":["GE Research, Niskayuna, NY","GE Research, Niskayuna, NY,"],"affiliations":[{"raw_affiliation_string":"GE Research, Niskayuna, NY","institution_ids":["https://openalex.org/I4210134512"]},{"raw_affiliation_string":"GE Research, Niskayuna, NY,","institution_ids":["https://openalex.org/I1332737386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109403205","display_name":"Ashwin Satyanarayana","orcid":null},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin Satyanarayana","raw_affiliation_strings":["SUNY Albany, Albany, NY","SUNY-Albany, Albany, NY"],"affiliations":[{"raw_affiliation_string":"SUNY Albany, Albany, NY","institution_ids":["https://openalex.org/I392282"]},{"raw_affiliation_string":"SUNY-Albany, Albany, NY","institution_ids":["https://openalex.org/I392282"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066946946","display_name":"Giri Kumar Tayi","orcid":"https://orcid.org/0000-0001-5505-0986"},"institutions":[{"id":"https://openalex.org/I392282","display_name":"University at Albany, State University of New York","ror":"https://ror.org/012zs8222","country_code":"US","type":"education","lineage":["https://openalex.org/I392282"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giri K. Tayi","raw_affiliation_strings":["SUNY Albany, Albany, NY","SUNY-Albany, Albany, NY"],"affiliations":[{"raw_affiliation_string":"SUNY Albany, Albany, NY","institution_ids":["https://openalex.org/I392282"]},{"raw_affiliation_string":"SUNY-Albany, Albany, NY","institution_ids":["https://openalex.org/I392282"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030289182"],"corresponding_institution_ids":["https://openalex.org/I392282"],"apc_list":null,"apc_paid":null,"fwci":0.4504,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.68278542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"794","last_page":"798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9977999925613403,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7583749890327454},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.610322117805481},{"id":"https://openalex.org/keywords/quality-assurance","display_name":"Quality assurance","score":0.6047730445861816},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5900296568870544},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5900142192840576},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5620375275611877},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.4843972325325012},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4624289572238922},{"id":"https://openalex.org/keywords/quality-management","display_name":"Quality management","score":0.45586326718330383},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.4461749196052551},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.44296520948410034},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.44150251150131226},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4194951355457306},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35149016976356506},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1269758641719818},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1003582775592804},{"id":"https://openalex.org/keywords/management-system","display_name":"Management system","score":0.08560642600059509},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08406543731689453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583749890327454},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.610322117805481},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.6047730445861816},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5900296568870544},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5900142192840576},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5620375275611877},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.4843972325325012},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4624289572238922},{"id":"https://openalex.org/C71405471","wikidata":"https://www.wikidata.org/wiki/Q757012","display_name":"Quality management","level":3,"score":0.45586326718330383},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.4461749196052551},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.44296520948410034},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.44150251150131226},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4194951355457306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35149016976356506},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1269758641719818},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1003582775592804},{"id":"https://openalex.org/C198783460","wikidata":"https://www.wikidata.org/wiki/Q629173","display_name":"Management system","level":2,"score":0.08560642600059509},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08406543731689453},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C2778618615","wikidata":"https://www.wikidata.org/wiki/Q4008393","display_name":"External quality assessment","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1014052.1016916","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1016916","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.7623","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.7623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.albany.edu/~davidson/Publications/kddind2004.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.91.9336","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.91.9336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.albany.edu/~davidson/Publications/Davidson105.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W194545673","https://openalex.org/W1516193414","https://openalex.org/W1522629397","https://openalex.org/W1530010412","https://openalex.org/W1983173467","https://openalex.org/W2015320147","https://openalex.org/W2022775778","https://openalex.org/W2065866673","https://openalex.org/W2088022181","https://openalex.org/W2128859147","https://openalex.org/W2912934387"],"related_works":["https://openalex.org/W2461248931","https://openalex.org/W962911587","https://openalex.org/W4200551113","https://openalex.org/W2270762093","https://openalex.org/W2094580389","https://openalex.org/W4255072332","https://openalex.org/W2028861106","https://openalex.org/W3126834064","https://openalex.org/W1754154538","https://openalex.org/W3169246587"],"abstract_inverted_index":{"Data":[0],"quality":[1,15,124,138,157,180],"is":[2,23,66,87,96,123,191],"a":[3,21,27,169,194],"central":[4],"issue":[5],"for":[6,140,162],"many":[7,48],"information-oriented":[8],"organizations.":[9],"Recent":[10],"advances":[11],"in":[12,155,196],"the":[13,18,24,52,59,62,73,85,93,113,131,134,141,175,184,189],"data":[14,45,63,114,137,142,176],"field":[16],"reflect":[17],"view":[19],"that":[20,149,173],"database":[22,86],"product":[25,60],"of":[26,61,70,75,92,121,133],"manufacturing":[28,53,64,115],"process.":[29],"While":[30],"routine":[31],"errors,":[32],"such":[33,103],"as":[34,104],"non-existent":[35],"zip":[36],"codes,":[37],"can":[38],"be":[39,56],"detected":[40],"and":[41,107,187],"corrected":[42],"using":[43],"traditional":[44],"cleansing":[46],"tools,":[47],"errors":[49],"systemic":[50],"to":[51,98,178,182,193],"process":[54,65],"cannot":[55],"addressed.":[57],"Therefore,":[58],"an":[67],"imprecise":[68],"recording":[69],"information":[71],"about":[72],"entities":[74,94],"interest":[76],"(i.e.":[77],"customers,":[78],"transactions":[79],"or":[80],"assets).":[81],"In":[82,126],"this":[83,127],"way,":[84],"only":[88],"one":[89],"(flawed)":[90],"version":[91],"it":[95],"supposed":[97],"represent.":[99],"Quality":[100],"assurance":[101],"systems":[102],"Motorola's":[105],"Six-Sigma":[106],"other":[108],"continuous":[109],"improvement":[110,190],"methods":[111],"document":[112],"process's":[116],"shortcomings.":[117],"A":[118],"widespread":[119],"method":[120],"documentation":[122],"matrices.":[125],"paper,":[128],"we":[129,151],"explore":[130],"use":[132],"readily":[135],"available":[136],"matrices":[139,181],"mining":[143],"classification":[144],"task.":[145],"We":[146,166],"first":[147],"illustrate":[148],"if":[150],"do":[152],"not":[153],"factor":[154],"these":[156,179],"matrices,":[158],"then":[159,167],"our":[160],"results":[161],"prediction":[163],"are":[164],"sub-optimal.":[165],"suggest":[168],"general-purpose":[170],"ensemble":[171],"approach":[172],"perturbs":[174],"according":[177],"improve":[183],"predictive":[185],"accuracy":[186],"show":[188],"due":[192],"reduction":[195],"variance.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
