{"id":"https://openalex.org/W4390723615","doi":"https://doi.org/10.1145/3639326","title":"In-Database Data Imputation","display_name":"In-Database Data Imputation","publication_year":2024,"publication_date":"2024-03-12","ids":{"openalex":"https://openalex.org/W4390723615","doi":"https://doi.org/10.1145/3639326"},"language":"en","primary_location":{"id":"doi:10.1145/3639326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639326","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639326","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3639326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002837048","display_name":"Massimo Perini","orcid":"https://orcid.org/0000-0001-5006-9979"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Massimo Perini","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5006-9979","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101550827","display_name":"Milo\u0161 Nikoli\u0107","orcid":"https://orcid.org/0000-0002-1548-6803"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Milos Nikolic","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-1548-6803","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":1.1114,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79396782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2","issue":"1","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9973000288009644,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9973000288009644,"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/T11719","display_name":"Data Quality and Management","score":0.9908999800682068,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9904999732971191,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.8182741403579712},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7700408697128296},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7563849687576294},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.7293806672096252},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6115421652793884},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.609582245349884},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.529176652431488},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5146806836128235},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.43451541662216187},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31116169691085815},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2369268834590912},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23210865259170532}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.8182741403579712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700408697128296},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7563849687576294},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.7293806672096252},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6115421652793884},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.609582245349884},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.529176652431488},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5146806836128235},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.43451541662216187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31116169691085815},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2369268834590912},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23210865259170532},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3639326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639326","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639326","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2401.03359","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.03359","pdf_url":"https://arxiv.org/pdf/2401.03359","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/496f912c-eb2d-4a1a-ad34-438db92503d7","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/496f912c-eb2d-4a1a-ad34-438db92503d7","pdf_url":"https://www.research.ed.ac.uk/files/404387635/In-Database_Data_Imputation_PERINI_DOA20112023_AFV_CC_BY.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Perini, M & Nikolic, M 2024, 'In-Database Data Imputation', Proceedings of the ACM on Management of Data, vol. 2, no. 1, 70, pp. 1-27. https://doi.org/10.1145/3639326","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3639326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639326","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639326","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5299999713897705},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390723615.pdf","grobid_xml":"https://content.openalex.org/works/W4390723615.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1537066827","https://openalex.org/W1965973862","https://openalex.org/W2032775418","https://openalex.org/W2044849727","https://openalex.org/W2090850279","https://openalex.org/W2100444372","https://openalex.org/W2101234009","https://openalex.org/W2115098571","https://openalex.org/W2116814040","https://openalex.org/W2124645273","https://openalex.org/W2134947937","https://openalex.org/W2284514301","https://openalex.org/W2402007731","https://openalex.org/W2437617937","https://openalex.org/W2544486974","https://openalex.org/W2547190417","https://openalex.org/W2563724055","https://openalex.org/W2591700809","https://openalex.org/W2612139288","https://openalex.org/W2750756391","https://openalex.org/W2798659310","https://openalex.org/W2803396353","https://openalex.org/W2803403013","https://openalex.org/W2808833850","https://openalex.org/W2889249015","https://openalex.org/W2891381594","https://openalex.org/W2897852178","https://openalex.org/W2948085204","https://openalex.org/W2962991166","https://openalex.org/W2970651950","https://openalex.org/W3003365835","https://openalex.org/W3006713198","https://openalex.org/W3029062663","https://openalex.org/W3030481596","https://openalex.org/W3031182173","https://openalex.org/W3032627613","https://openalex.org/W3082197983","https://openalex.org/W3086660971","https://openalex.org/W3086663505","https://openalex.org/W3094678421","https://openalex.org/W3125213913","https://openalex.org/W3147796863","https://openalex.org/W3169654496","https://openalex.org/W3173807324","https://openalex.org/W3179164182","https://openalex.org/W3183875135","https://openalex.org/W3197847098","https://openalex.org/W3198445485","https://openalex.org/W3212918802","https://openalex.org/W4206065759","https://openalex.org/W4210394794","https://openalex.org/W4221154908","https://openalex.org/W4225744774","https://openalex.org/W4230289604","https://openalex.org/W4243565423","https://openalex.org/W4312632526","https://openalex.org/W4317767732","https://openalex.org/W4386123448","https://openalex.org/W6675354045","https://openalex.org/W6959643953"],"related_works":["https://openalex.org/W2181530120","https://openalex.org/W4211215373","https://openalex.org/W2024529227","https://openalex.org/W2055961818","https://openalex.org/W2519761320","https://openalex.org/W1574575415","https://openalex.org/W3144172081","https://openalex.org/W3179858851","https://openalex.org/W3028371478","https://openalex.org/W2081476516"],"abstract_inverted_index":{"Missing":[0],"data":[1,12,87],"is":[2],"a":[3,54,90,108],"widespread":[4],"problem":[5],"in":[6,11,64,140,159],"many":[7],"domains,":[8],"creating":[9],"challenges":[10],"analysis":[13,135],"and":[14,42,62,85,107,119,132,142,148],"decision":[15],"making.":[16],"Traditional":[17],"techniques":[18,52,124,151],"for":[19,111,125],"dealing":[20],"with":[21],"missing":[22],"data,":[23,66],"such":[24],"as":[25],"excluding":[26],"incomplete":[27],"records":[28],"or":[29],"imputing":[30],"simple":[31],"estimates":[32],"(e.g.,":[33],"mean),":[34],"are":[35],"computationally":[36],"efficient":[37],"but":[38,67],"may":[39],"introduce":[40],"bias":[41],"disrupt":[43],"variable":[44],"relationships,":[45],"leading":[46],"to":[47,77,103,154],"inaccurate":[48],"analyses.":[49],"Model-based":[50],"imputation":[51,88,150,167],"offer":[53],"more":[55,71],"robust":[56],"solution":[57],"that":[58],"preserves":[59],"the":[60,65,94],"variability":[61],"relationships":[63],"they":[68],"demand":[69],"significantly":[70],"computation":[72,105,162],"time,":[73,163],"limiting":[74],"their":[75],"applicability":[76],"small":[78],"datasets.":[79],"This":[80],"work":[81],"enables":[82],"efficient,":[83],"high-quality,":[84],"scalable":[86],"within":[89],"database":[91],"system":[92],"using":[93],"widely":[95],"used":[96],"MICE":[97,138,146],"method.":[98],"We":[99],"adapt":[100],"this":[101],"method":[102],"exploit":[104],"sharing":[106],"ring":[109],"abstraction":[110],"faster":[112],"model":[113],"training.":[114],"To":[115],"impute":[116],"both":[117],"continuous":[118],"categorical":[120],"values,":[121],"we":[122],"develop":[123],"in-database":[126],"learning":[127],"of":[128,157,161],"stochastic":[129],"linear":[130],"regression":[131],"Gaussian":[133],"discriminant":[134],"models.":[136],"Our":[137],"implementations":[139,147],"PostgreSQL":[141],"DuckDB":[143],"outperform":[144],"alternative":[145],"model-based":[149],"by":[152],"up":[153],"two":[155],"orders":[156],"magnitude":[158],"terms":[160],"while":[164],"maintaining":[165],"high":[166],"quality.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}