{"id":"https://openalex.org/W3194405061","doi":"https://doi.org/10.1145/3447548.3470817","title":"Data Quality for Machine Learning Tasks","display_name":"Data Quality for Machine Learning Tasks","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3194405061","doi":"https://doi.org/10.1145/3447548.3470817","mag":"3194405061"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3470817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3470817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","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/A5054069765","display_name":"Nitin Gupta","orcid":"https://orcid.org/0000-0003-0177-6292"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nitin Gupta","raw_affiliation_strings":["IBM Research India, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054372047","display_name":"Shashank Mujumdar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashank Mujumdar","raw_affiliation_strings":["IBM Research India, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Delhi, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102917997","display_name":"Hima Patel","orcid":"https://orcid.org/0000-0002-0031-8428"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hima Patel","raw_affiliation_strings":["IBM Research India, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027343222","display_name":"Satoshi Masuda","orcid":"https://orcid.org/0000-0002-5633-7249"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Masuda","raw_affiliation_strings":["IBM Research Japan, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Japan, Tokyo, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041018414","display_name":"Naveen Panwar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Naveen Panwar","raw_affiliation_strings":["IBM Research India, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102391724","display_name":"Sambaran Bandyopadhyay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sambaran Bandyopadhyay","raw_affiliation_strings":["IBM Research India, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046646390","display_name":"Sameep Mehta","orcid":"https://orcid.org/0000-0002-9599-1526"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sameep Mehta","raw_affiliation_strings":["IBM Research India, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082881366","display_name":"Shanmukha Guttula","orcid":"https://orcid.org/0009-0001-1982-024X"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shanmukha Guttula","raw_affiliation_strings":["IBM Research India, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505239","display_name":"Shazia Afzal","orcid":"https://orcid.org/0000-0001-7151-4306"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shazia Afzal","raw_affiliation_strings":["IBM Research India, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046316553","display_name":"Ruhi Sharma Mittal","orcid":"https://orcid.org/0009-0002-2649-6844"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ruhi Sharma Mittal","raw_affiliation_strings":["IBM Research India, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011547127","display_name":"Vitobha Munigala","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vitobha Munigala","raw_affiliation_strings":["IBM Research India, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research India, Bengaluru, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.077,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.98495023,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4040","last_page":"4041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9976999759674072,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11719","display_name":"Data Quality and Management","score":0.9943000078201294,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.846000611782074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6675454378128052},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5752772092819214},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5544556379318237},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5422940254211426},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.5327855348587036},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5158187747001648},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.477211058139801},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.467441201210022},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4617706835269928},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4535468816757202},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4017345905303955},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.310211181640625},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07693728804588318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.846000611782074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6675454378128052},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5752772092819214},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5544556379318237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5422940254211426},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.5327855348587036},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5158187747001648},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.477211058139801},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.467441201210022},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4617706835269928},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4535468816757202},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4017345905303955},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.310211181640625},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07693728804588318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447548.3470817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3470817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W70001371","https://openalex.org/W1541033774","https://openalex.org/W1552339598","https://openalex.org/W2622411536","https://openalex.org/W2914436728","https://openalex.org/W2963214893","https://openalex.org/W2985783697","https://openalex.org/W2998184481","https://openalex.org/W3023533951","https://openalex.org/W3035748261","https://openalex.org/W3088611441","https://openalex.org/W4252280335"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W1596854558","https://openalex.org/W2902823524","https://openalex.org/W4245815800","https://openalex.org/W2499364091","https://openalex.org/W4385985500"],"abstract_inverted_index":{"The":[0],"quality":[1,73],"of":[2,15,41,74],"training":[3],"data":[4,42,83],"has":[5],"a":[6],"huge":[7],"impact":[8],"on":[9,70],"the":[10,72,82],"efficiency,":[11],"accuracy":[12],"and":[13,39,51,61,66],"complexity":[14],"machine":[16,48],"learning":[17,49],"tasks.":[18],"Data":[19],"remains":[20],"susceptible":[21],"to":[22,43,53],"errors":[23],"or":[24,33],"irregularities":[25],"that":[26],"may":[27],"be":[28],"introduced":[29],"during":[30],"collection,":[31],"aggregation":[32],"annotation":[34],"stage.":[35],"This":[36],"necessitates":[37],"profiling":[38],"assessment":[40],"understand":[44],"its":[45],"suitability":[46],"for":[47],"tasks":[50],"failure":[52],"do":[54],"so":[55],"can":[56],"result":[57],"in":[58],"inaccurate":[59],"analytics":[60],"unreliable":[62],"decisions.":[63],"While":[64],"researchers":[65],"practitioners":[67],"have":[68],"focused":[69],"improving":[71,81],"models,":[75],"there":[76],"are":[77],"limited":[78],"efforts":[79],"towards":[80],"quality.":[84]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":3}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}