{"id":"https://openalex.org/W4385562494","doi":"https://doi.org/10.1145/3580305.3599911","title":"The Missing Indicator Method: From Low to High Dimensions","display_name":"The Missing Indicator Method: From Low to High Dimensions","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385562494","doi":"https://doi.org/10.1145/3580305.3599911"},"language":"en","primary_location":{"id":"doi:10.1145/3580305.3599911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD 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/A5022335506","display_name":"Mike Van Ness","orcid":"https://orcid.org/0000-0002-7829-8164"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mike Van Ness","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007040994","display_name":"Tomas M. Bosschieter","orcid":"https://orcid.org/0000-0001-9726-6400"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tomas M. Bosschieter","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005289145","display_name":"Roberto Halpin-Gregorio","orcid":"https://orcid.org/0009-0004-0154-9967"},"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":"Roberto Halpin-Gregorio","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084564811","display_name":"Madeleine Udell","orcid":"https://orcid.org/0000-0002-3985-915X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madeleine Udell","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022335506"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.0061,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87667532,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5004","last_page":"5015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9911999702453613,"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":0.9911999702453613,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9909999966621399,"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":0.9900000095367432,"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/missing-data","display_name":"Missing data","score":0.9587705135345459},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.8693881034851074},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8098843097686768},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.67205411195755},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.519263744354248},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.45385417342185974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38520729541778564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.348215788602829},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16936549544334412}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.9587705135345459},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.8693881034851074},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8098843097686768},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67205411195755},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.519263744354248},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.45385417342185974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38520729541778564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.348215788602829},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16936549544334412}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3580305.3599911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3580305.3599911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W612972800","https://openalex.org/W1822348759","https://openalex.org/W1967524919","https://openalex.org/W2049633694","https://openalex.org/W2064186732","https://openalex.org/W2065709315","https://openalex.org/W2068331431","https://openalex.org/W2078965693","https://openalex.org/W2100358124","https://openalex.org/W2110065044","https://openalex.org/W2115098571","https://openalex.org/W2122717603","https://openalex.org/W2132862423","https://openalex.org/W2295598076","https://openalex.org/W2597505554","https://openalex.org/W2735864302","https://openalex.org/W2788592841","https://openalex.org/W2806031239","https://openalex.org/W2908218180","https://openalex.org/W2910420059","https://openalex.org/W2932881901","https://openalex.org/W2952482786","https://openalex.org/W2965722814","https://openalex.org/W2997591727","https://openalex.org/W3035639029","https://openalex.org/W3036815702","https://openalex.org/W3040007568","https://openalex.org/W3080381655","https://openalex.org/W3080534420","https://openalex.org/W3091927171","https://openalex.org/W3101826436","https://openalex.org/W3101973032","https://openalex.org/W3183580055","https://openalex.org/W3197494818","https://openalex.org/W4287556785","https://openalex.org/W4288083420","https://openalex.org/W4389138872"],"related_works":["https://openalex.org/W2181530120","https://openalex.org/W4211215373","https://openalex.org/W2024529227","https://openalex.org/W2055961818","https://openalex.org/W1574575415","https://openalex.org/W3144172081","https://openalex.org/W3179858851","https://openalex.org/W3028371478","https://openalex.org/W2081476516","https://openalex.org/W2581984549"],"abstract_inverted_index":{"Missing":[0,65],"data":[1,6,11,42,58,93,143,212],"is":[2,96],"common":[3],"in":[4,14,81,92,195],"applied":[5],"science,":[7,94],"particularly":[8],"for":[9,118,133,141,176,200],"tabular":[10],"sets":[12,59,144],"found":[13],"healthcare,":[15],"social":[16],"sciences,":[17],"and":[18,102,112,122,154,197,221],"natural":[19],"sciences.":[20],"Most":[21],"supervised":[22],"learning":[23],"methods":[24],"only":[25,175],"work":[26,39],"on":[27,40,210,223],"complete":[28],"data,":[29],"thus":[30,155],"requiring":[31],"preprocessing":[32],"such":[33],"as":[34,191,193],"missing":[35,54,62,76,120,135,173,181],"value":[36],"imputation":[37,45,84],"to":[38,73,85,204],"incomplete":[41],"sets.":[43],"However,":[44],"alone":[46],"does":[47,127],"not":[48,128],"encode":[49],"useful":[50],"information":[51],"about":[52],"the":[53,64,75,206,217,228],"values":[55],"themselves.":[56],"For":[57],"with":[60,83,145],"informative":[61,119,180],"patterns,":[63],"Indicator":[66],"Method":[67],"(MIM),":[68],"which":[69],"adds":[70,172],"indicator":[71],"variables":[72],"indicate":[74],"pattern,":[77],"can":[78,150],"be":[79],"used":[80,91],"conjunction":[82],"improve":[86],"model":[87,152],"performance.":[88,157],"While":[89],"commonly":[90],"MIM":[95,115,126,149,165,169,194,199,209,220],"surprisingly":[97],"understudied":[98],"from":[99,227],"an":[100],"empirical":[101],"especially":[103],"theoretical":[104],"perspective.":[105],"In":[106],"this":[107,160],"paper,":[108],"we":[109,123,138,162,215],"show":[110,184],"empirically":[111,185],"theoretically":[113],"that":[114,125,140,171,178,186],"improves":[116,198],"performance":[117],"values,":[121],"prove":[124],"hurt":[129],"linear":[130],"models":[131],"asymptotically":[132],"uninformative":[134,147],"values.":[136],"Additionally,":[137],"find":[139],"high-dimensional":[142,201],"many":[146],"indicators,":[148],"induce":[151],"overfitting":[153],"test":[156],"To":[158],"address":[159],"issue,":[161],"introduce":[163],"Selective":[164],"(SMIM),":[166],"a":[167],"novel":[168],"extension":[170],"indicators":[174],"features":[177],"have":[179],"patterns.":[182],"We":[183],"SMIM":[187,222],"performs":[188],"at":[189],"least":[190],"well":[192],"general,":[196],"data.":[202],"Lastly,":[203],"demonstrate":[205,216],"utility":[207],"of":[208,219,231],"real-world":[211],"science":[213],"tasks,":[214],"effectiveness":[218],"clinical":[224],"tasks":[225],"generated":[226],"MIMIC-III":[229],"database":[230],"electronic":[232],"health":[233],"records.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}