@prefix this: . @prefix sub: . @prefix np: . @prefix dct: . @prefix pav: . @prefix nt: . @prefix npx: . @prefix xsd: . @prefix rdfs: . @prefix orcid: . @prefix ns1: . @prefix prov: . @prefix foaf: . sub:Head { this: np:hasAssertion sub:assertion ; np:hasProvenance sub:provenance ; np:hasPublicationInfo sub:pubinfo ; a np:Nanopublication . } sub:assertion { dct:title "Data Science" . dct:abstract "Measuring data drift is essential in machine learning applications where model scoring (evaluation) is done on data samples that differ from those used in training. The Kullback-Leibler divergence is a common measure of shifted probability distributions, for which discretized versions are invented to deal with binned or categorical data. We present the Unstable Population Indicator, a robust, flexible and numerically stable, discretized implementation of Jeffrey's divergence, along with an implementation in a Python package that can deal with continuous, discrete, ordinal and nominal data in a variety of popular data types. We show the numerical and statistical properties in controlled experiments. It is not advised to employ a common cut-off to distinguish stable from unstable populations, but rather to let that cut-off depend on the use case." ; dct:date "2024" ; dct:hasPart ; dct:isPartOf ; dct:title "Measuring Data Drift with the Unstable Population Indicator" ; pav:authoredBy orcid:0000-0003-2581-8370 , orcid:0009-0003-5030-0108 ; a . orcid:0000-0003-2581-8370 , ; "datascience@marcelhaas.com" ; a foaf:Person ; foaf:name "Marcel R. Haas" . orcid:0009-0003-5030-0108 , ; "L.Sibbald@tilburguniversity.edu" ; a foaf:Person ; foaf:name "Lisette Sibbald" . a foaf:Organization ; foaf:name "Department of Methodology and Statistics and Department of Cognitive Neuropsychology, Tilburg University, Prof. Cobbenhagenlaan 125, 5037 DB Tilburg, The Netherlands" . a foaf:Organization ; foaf:name "Business Intelligence, University of Amsterdam, Spui 21, 1012WX Amsterdam, The Netherlands" . a foaf:Organization ; foaf:name "Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, The Netherlands" . } sub:provenance { sub:assertion prov:wasAttributedTo orcid:0000-0003-2581-8370 , orcid:0009-0003-5030-0108 . } sub:pubinfo { orcid:0000-0002-1267-0234 foaf:name "Tobias Kuhn" . sub:sig npx:hasAlgorithm "RSA" ; npx:hasPublicKey "MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCjDGQCS1S+SRnERDuYDXOugdYUP0efEquHJEEHAbU/uLzBVlga89zqrNPCS7fBE6lArBUWEmT8eLKdMapyqvAzI1J3jUWTMhDJF+XFBkUiuiFfNSc4vJJcmi0yujtnuzXsRIG202jyaP4f5ULoskFwaZOSBZJfiE0dsB3D7DTIAQIDAQAB" ; npx:hasSignature "jCn+zSfYA3AOGtip/isskdZG5kc8nbrq9d7rETWmKb/Ao2OiCKrgt7ER2r5QrtPorFwCAP/8iAUkD241v9yjI7uqpyT1BnZ0yzkgSFwAjo/aqKopKCGbGQ+0sHtaPUYsxhd7wvZsXXHI0xFo2sQM8ibI2Z8edhsHLvrvDssIKDg=" ; npx:hasSignatureTarget this: ; npx:signedBy orcid:0000-0002-1267-0234 . this: dct:created "2024-02-29T09:53:47.853Z"^^xsd:dateTime ; dct:creator orcid:0000-0002-1267-0234 ; dct:license ; npx:hasNanopubType , ; npx:introduces ; npx:supersedes ; npx:wasCreatedAt ; rdfs:label "Article: Measuring Data Drift with the Unstable Population Indicator" ; nt:wasCreatedFromProvenanceTemplate ns1:RAi6zZAwhaJ23Hzg4lIjlPir6Take3ZQp-lS9skfBEwfQ ; nt:wasCreatedFromPubinfoTemplate ns1:RAA2MfqdBCzmz9yVWjKLXNbyfBNcwsMmOqcNUxkk1maIM , ns1:RAh1gm83JiG5M6kDxXhaYT1l49nCzyrckMvTzcPn-iv90 , ns1:RAjpBMlw3owYhJUBo3DtsuDlXsNAJ8cnGeWAutDVjuAuI , ; nt:wasCreatedFromTemplate . }