{"id":"https://openalex.org/W2018447176","doi":"https://doi.org/10.1145/1014052.1014121","title":"Diagnosing extrapolation","display_name":"Diagnosing extrapolation","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2018447176","doi":"https://doi.org/10.1145/1014052.1014121","mag":"2018447176"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international 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/A5078275541","display_name":"Giles Hooker","orcid":"https://orcid.org/0000-0003-2648-1167"},"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":"Giles Hooker","raw_affiliation_strings":["Stanford University, Stanford, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078275541"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.4497,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.74285967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"569","last_page":"574"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9950000047683716,"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":0.9950000047683716,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9940999746322632,"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/T11443","display_name":"Advanced Statistical Process Monitoring","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"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/extrapolation","display_name":"Extrapolation","score":0.9650173187255859},{"id":"https://openalex.org/keywords/test-statistic","display_name":"Test statistic","score":0.5755945444107056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5676829218864441},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.522061288356781},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.46876853704452515},{"id":"https://openalex.org/keywords/null-hypothesis","display_name":"Null hypothesis","score":0.44075414538383484},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4397386610507965},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.428419291973114},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4255630373954773},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41088417172431946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4091336727142334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3838012218475342},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37939882278442383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37670037150382996},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3497292399406433},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3271811008453369}],"concepts":[{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.9650173187255859},{"id":"https://openalex.org/C169857963","wikidata":"https://www.wikidata.org/wiki/Q1461038","display_name":"Test statistic","level":3,"score":0.5755945444107056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5676829218864441},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.522061288356781},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.46876853704452515},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.44075414538383484},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4397386610507965},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.428419291973114},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4255630373954773},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41088417172431946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4091336727142334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3838012218475342},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37939882278442383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37670037150382996},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3497292399406433},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3271811008453369},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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":1,"locations":[{"id":"doi:10.1145/1014052.1014121","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1504694836","https://openalex.org/W1594031697","https://openalex.org/W1678356000","https://openalex.org/W2029469881","https://openalex.org/W2125055259","https://openalex.org/W3085162807","https://openalex.org/W6843735874"],"related_works":["https://openalex.org/W1970221037","https://openalex.org/W2488034322","https://openalex.org/W2102421359","https://openalex.org/W4254912865","https://openalex.org/W2042536588","https://openalex.org/W4285309165","https://openalex.org/W2006467890","https://openalex.org/W2035871637","https://openalex.org/W2185794042","https://openalex.org/W4382599617"],"abstract_inverted_index":{"There":[0],"has":[1],"historically":[2],"been":[3],"very":[4,34,45],"little":[5],"concern":[6],"with":[7,105],"extrapolation":[8,13,121],"in":[9,84,94,97],"Machine":[10],"Learning,":[11],"yet":[12],"can":[14,90,161],"be":[15,91,162],"critical":[16],"to":[17,77,136,145,164],"diagnose.":[18],"Predictor":[19],"functions":[20],"are":[21,47,75],"almost":[22],"always":[23],"learned":[24],"on":[25,64],"a":[26,33,56,65,79,92,118,123,127,137,153,173],"set":[27],"of":[28,37,52,114,185,188,194],"highly":[29],"correlated":[30],"data":[31,132],"comprising":[32],"small":[35],"segment":[36],"predictor":[38,101],"space.":[39,87],"Moreover,":[40],"flexible":[41],"predictors,":[42],"by":[43],"their":[44],"nature,":[46],"not":[48],"controlled":[49],"at":[50],"points":[51],"extrapolation.":[53],"This":[54,142],"becomes":[55,178],"problem":[57,93],"for":[58,120,126,150],"diagnostic":[59],"tools":[60],"that":[61,159],"require":[62],"evaluation":[63],"product":[66],"distribution.":[67,141],"It":[68],"is":[69],"also":[70],"an":[71,166,170],"issue":[72],"when":[73,108],"we":[74,157],"trying":[76],"optimize":[78],"response":[80],"over":[81],"some":[82,115,184],"variable":[83],"the":[85,99,112,131,186],"input":[86],"Finally,":[88],"it":[89],"non-static":[95],"systems":[96],"which":[98,177],"underlying":[100],"distribution":[102,133,168],"gradually":[103],"drifts":[104],"time":[106],"or":[107],"typographical":[109],"errors":[110],"misrecord":[111],"values":[113],"predictors.We":[116],"present":[117,192],"diagnosis":[119],"as":[122,134,169],"statistical":[124],"test":[125,154],"point":[128],"originating":[129],"from":[130],"opposed":[135],"null":[138],"hypothesis":[139],"uniform":[140],"allows":[143],"us":[144],"employ":[146],"general":[147],"classification":[148,175],"methods":[149],"estimating":[151],"such":[152],"statistic.":[155],"Further,":[156],"observe":[158],"CART":[160],"modified":[163],"accept":[165],"exact":[167],"argument,":[171],"providing":[172],"better":[174],"tool":[176],"our":[179],"extrapolation-detection":[180],"procedure.":[181],"We":[182],"explore":[183],"advantages":[187],"this":[189],"approach":[190],"and":[191],"examples":[193],"its":[195],"practical":[196],"application.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}