{"id":"https://openalex.org/W4392386944","doi":"https://doi.org/10.3233/ds-240059","title":"Measuring data drift with the unstable population indicator","display_name":"Measuring data drift with the unstable population indicator","publication_year":2024,"publication_date":"2024-03-01","ids":{"openalex":"https://openalex.org/W4392386944","doi":"https://doi.org/10.3233/ds-240059"},"language":"en","primary_location":{"id":"doi:10.3233/ds-240059","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ds-240059","pdf_url":"https://content.iospress.com:443/download/data-science/ds240059?id=data-science%2Fds240059","source":{"id":"https://openalex.org/S4210178722","display_name":"Data Science","issn_l":"2451-8484","issn":["2451-8484","2451-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://content.iospress.com:443/download/data-science/ds240059?id=data-science%2Fds240059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072790276","display_name":"M. Haas","orcid":"https://orcid.org/0000-0003-2581-8370"},"institutions":[{"id":"https://openalex.org/I2800006345","display_name":"Leiden University Medical Center","ror":"https://ror.org/05xvt9f17","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800006345"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Marcel R. Haas","raw_affiliation_strings":["Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, The Netherlands and Business Intelligence, University of Amsterdam, Spui 21, 1012WX Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0003-2581-8370","affiliations":[{"raw_affiliation_string":"Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, The Netherlands and Business Intelligence, University of Amsterdam, Spui 21, 1012WX Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I2800006345","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5094051240","display_name":"Lisette Sibbald","orcid":"https://orcid.org/0009-0003-5030-0108"},"institutions":[{"id":"https://openalex.org/I193700539","display_name":"Tilburg University","ror":"https://ror.org/04b8v1s79","country_code":"NL","type":"education","lineage":["https://openalex.org/I193700539"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lisette Sibbald","raw_affiliation_strings":["Department of Methodology and Statistics, Tilburg University, Prof. Cobbenhagenlaan 125, 5037 DB Tilburg, The Netherlands and Department of Cognitive Neuropsychology, Tilburg University, Prof. Cobbenhagenlaan 125, 5037 DB Tilburg, The Netherlands and Business Intelligence, University of Amsterdam, Spui 21, 1012WX Amsterdam, The Netherlands","Tilburg University, Prof. Cobbenhagenlaan 125, 5037 DB Tilburg, The Netherlands and Business Intelligence,","University of Amsterdam, Spui 21, 1012WX Amsterdam, The Netherlands"],"raw_orcid":"https://orcid.org/0009-0003-5030-0108","affiliations":[{"raw_affiliation_string":"Department of Methodology and Statistics, Tilburg University, Prof. Cobbenhagenlaan 125, 5037 DB Tilburg, The Netherlands and Department of Cognitive Neuropsychology, Tilburg University, Prof. Cobbenhagenlaan 125, 5037 DB Tilburg, The Netherlands and Business Intelligence, University of Amsterdam, Spui 21, 1012WX Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I193700539","https://openalex.org/I887064364"]},{"raw_affiliation_string":"Tilburg University, Prof. Cobbenhagenlaan 125, 5037 DB Tilburg, The Netherlands and Business Intelligence,","institution_ids":["https://openalex.org/I193700539"]},{"raw_affiliation_string":"University of Amsterdam, Spui 21, 1012WX Amsterdam, The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072790276"],"corresponding_institution_ids":["https://openalex.org/I2800006345","https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.4788,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68669638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"7","issue":"1","first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9914000034332275,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9914000034332275,"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/T11918","display_name":"Forecasting Techniques and Applications","score":0.9753999710083008,"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/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.9480999708175659,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.777681827545166},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.7765332460403442},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.7090204954147339},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6793172955513},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5410503149032593},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.49163419008255005},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.47649210691452026},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.44536393880844116},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4442436099052429},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38778361678123474},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.38573455810546875},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.37484365701675415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3256566822528839},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10589537024497986}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.777681827545166},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.7765332460403442},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7090204954147339},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6793172955513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5410503149032593},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.49163419008255005},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.47649210691452026},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.44536393880844116},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4442436099052429},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38778361678123474},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.38573455810546875},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.37484365701675415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3256566822528839},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10589537024497986},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3233/ds-240059","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ds-240059","pdf_url":"https://content.iospress.com:443/download/data-science/ds240059?id=data-science%2Fds240059","source":{"id":"https://openalex.org/S4210178722","display_name":"Data Science","issn_l":"2451-8484","issn":["2451-8484","2451-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science","raw_type":"journal-article"},{"id":"pmh:oai:tilburguniversity.edu:openaire/f18d9582-1c39-4e1c-9da6-f49bca817b56","is_oa":true,"landing_page_url":"https://research.tilburguniversity.edu/en/publications/f18d9582-1c39-4e1c-9da6-f49bca817b56","pdf_url":null,"source":{"id":"https://openalex.org/S4306401490","display_name":"Research portal (Tilburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193700539","host_organization_name":"Tilburg University","host_organization_lineage":["https://openalex.org/I193700539"],"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":"Haas, M R & Sibbald, L 2024, 'Measuring data drift with the unstable population indicator', Data Science, vol. 7, no. 1, 1, pp. 1-12. https://doi.org/10.3233/DS-240059","raw_type":"article"},{"id":"pmh:oai:tilburguniversity.edu:openaire_cris_publications/f18d9582-1c39-4e1c-9da6-f49bca817b56","is_oa":true,"landing_page_url":"https://repository.tilburguniversity.edu/bitstreams/f9345c2a-0184-4969-8460-9e5e84474169/download","pdf_url":null,"source":{"id":"https://openalex.org/S4306401490","display_name":"Research portal (Tilburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193700539","host_organization_name":"Tilburg University","host_organization_lineage":["https://openalex.org/I193700539"],"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":"Haas, M R & Sibbald, L 2024, 'Measuring data drift with the unstable population indicator', Data Science, vol. 7, no. 1, 1, pp. 1-12. https://doi.org/10.3233/DS-240059","raw_type":"article"},{"id":"pmh:oai:doaj.org/article:e0b07f8da1744c2d989db8dadc323a3d","is_oa":true,"landing_page_url":"https://doaj.org/article/e0b07f8da1744c2d989db8dadc323a3d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3233/ds-240059","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ds-240059","pdf_url":"https://content.iospress.com:443/download/data-science/ds240059?id=data-science%2Fds240059","source":{"id":"https://openalex.org/S4210178722","display_name":"Data Science","issn_l":"2451-8484","issn":["2451-8484","2451-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392386944.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W1487801014","https://openalex.org/W1965555277","https://openalex.org/W1995875735","https://openalex.org/W2011301426","https://openalex.org/W2146950091","https://openalex.org/W2162651021","https://openalex.org/W2342249984","https://openalex.org/W2791425844","https://openalex.org/W2891560655","https://openalex.org/W2942648925","https://openalex.org/W2993383518","https://openalex.org/W3035965352","https://openalex.org/W3099878876","https://openalex.org/W3150635270","https://openalex.org/W3203380512","https://openalex.org/W3212559860","https://openalex.org/W6969259846","https://openalex.org/W6977806375"],"related_works":["https://openalex.org/W2105321464","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W3048739257","https://openalex.org/W1665563134","https://openalex.org/W2963604926","https://openalex.org/W1616881371","https://openalex.org/W1520875569","https://openalex.org/W2199957582","https://openalex.org/W2033178790"],"abstract_inverted_index":{"Measuring":[0],"data":[1,16,83,89],"drift":[2],"is":[3,13,28,102],"essential":[4],"in":[5,23,70,84,98],"machine":[6],"learning":[7],"applications":[8],"where":[9],"model":[10],"scoring":[11],"(evaluation)":[12],"done":[14],"on":[15,123],"samples":[17],"that":[18,74,120],"differ":[19],"from":[20,113],"those":[21],"used":[22],"training.":[24],"The":[25],"Kullback-Leibler":[26],"divergence":[27],"a":[29,55,71,85,107],"common":[30,108],"measure":[31],"of":[32,63,87],"shifted":[33],"probability":[34],"distributions,":[35],"for":[36],"which":[37],"discretized":[38,61],"versions":[39],"are":[40],"invented":[41],"to":[42,105,110,118],"deal":[43,76],"with":[44,67,77],"binned":[45],"or":[46],"categorical":[47],"data.":[48],"We":[49,91],"present":[50],"the":[51,93,124],"Unstable":[52],"Population":[53],"Indicator,":[54],"robust,":[56],"flexible":[57],"and":[58,81,95],"numerically":[59],"stable,":[60],"implementation":[62,69],"Jeffrey\u2019s":[64],"divergence,":[65],"along":[66],"an":[68],"Python":[72],"package":[73],"can":[75],"continuous,":[78],"discrete,":[79],"ordinal":[80],"nominal":[82],"variety":[86],"popular":[88],"types.":[90],"show":[92],"numerical":[94],"statistical":[96],"properties":[97],"controlled":[99],"experiments.":[100],"It":[101],"not":[103],"advised":[104],"employ":[106],"cut-off":[109,121],"distinguish":[111],"stable":[112],"unstable":[114],"populations,":[115],"but":[116],"rather":[117],"let":[119],"depend":[122],"use":[125],"case.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}