{"id":"https://openalex.org/W4389316291","doi":"https://doi.org/10.1145/3636341.3636358","title":"A Common Misassumption in Online Experiments with Machine Learning Models","display_name":"A Common Misassumption in Online Experiments with Machine Learning Models","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4389316291","doi":"https://doi.org/10.1145/3636341.3636358"},"language":"en","primary_location":{"id":"doi:10.1145/3636341.3636358","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3636341.3636358","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"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":"ACM SIGIR Forum","raw_type":"journal-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/A5083237271","display_name":"Olivier Jeunen","orcid":"https://orcid.org/0000-0001-6256-5814"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Olivier Jeunen","raw_affiliation_strings":["ShareChat, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"ShareChat, Edinburgh, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5083237271"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4339,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90560738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"57","issue":"1","first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9979000091552734,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.9979000091552734,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9872999787330627,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9847000241279602,"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/computer-science","display_name":"Computer science","score":0.8297848105430603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7492392063140869},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6523744463920593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6258812546730042},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5070114135742188},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.49875974655151367},{"id":"https://openalex.org/keywords/randomized-experiment","display_name":"Randomized experiment","score":0.44171440601348877},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.43655189871788025},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3866318464279175},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.22889313101768494},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1701394021511078},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12224459648132324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297848105430603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7492392063140869},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6523744463920593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6258812546730042},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5070114135742188},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.49875974655151367},{"id":"https://openalex.org/C155108698","wikidata":"https://www.wikidata.org/wiki/Q1231081","display_name":"Randomized experiment","level":2,"score":0.44171440601348877},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.43655189871788025},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3866318464279175},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.22889313101768494},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1701394021511078},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12224459648132324},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3636341.3636358","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3636341.3636358","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"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":"ACM SIGIR Forum","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W141877818","https://openalex.org/W1985476803","https://openalex.org/W1998498767","https://openalex.org/W2163162311","https://openalex.org/W2511414107","https://openalex.org/W2604272474","https://openalex.org/W2784068709","https://openalex.org/W2946387282","https://openalex.org/W2972520532","https://openalex.org/W3011423189","https://openalex.org/W3042645155","https://openalex.org/W3099420497","https://openalex.org/W3150893739","https://openalex.org/W3166529875","https://openalex.org/W4205470728","https://openalex.org/W4226199487","https://openalex.org/W4242069725","https://openalex.org/W4290877189","https://openalex.org/W4290927948","https://openalex.org/W4297730339","https://openalex.org/W4318710454","https://openalex.org/W6676077707","https://openalex.org/W6810658271"],"related_works":["https://openalex.org/W4389471064","https://openalex.org/W2119346805","https://openalex.org/W3005312434","https://openalex.org/W4388998033","https://openalex.org/W4313559754","https://openalex.org/W1730782591","https://openalex.org/W2510789027","https://openalex.org/W3160537436","https://openalex.org/W2587735541","https://openalex.org/W4366197068"],"abstract_inverted_index":{"Online":[0],"experiments":[1,187],"such":[2],"as":[3,74],"Randomised":[4],"Controlled":[5],"Trials":[6],"(RCTs)":[7],"or":[8],"A/B-tests":[9,146],"are":[10,22,141,154],"the":[11,19,30,59,75,106,123,138,151,180,194,202],"bread":[12],"and":[13,84,111,200],"butter":[14],"of":[15,33,44,108,118,126,150,172],"modern":[16],"platforms":[17,27],"on":[18,41,58,92],"web.":[20],"They":[21],"conducted":[23],"continuously":[24],"to":[25,28,65,78,105,143],"allow":[26],"estimate":[29],"causal":[31,93,152],"effect":[32,94],"replacing":[34],"system":[35],"variant":[36,39],"\"A\"":[37],"with":[38,188],"\"B\",":[40],"some":[42],"metric":[43],"interest.":[45],"These":[46],"variants":[47,164],"can":[48,183],"differ":[49],"in":[50,114,122,157],"many":[51],"aspects.":[52],"In":[53],"this":[54,115,196],"paper,":[55],"we":[56,130,182],"focus":[57],"common":[60],"use-case":[61],"where":[62],"they":[63],"correspond":[64],"machine":[66,127,189],"learning":[67,128,190],"models.":[68,191],"The":[69,89],"online":[70,186],"experiment":[71],"then":[72],"serves":[73],"final":[76],"arbiter":[77],"decide":[79],"which":[80,102],"model":[81,173],"is":[82],"superior,":[83],"should":[85],"thus":[86],"be":[87,176],"shipped.":[88],"statistical":[90],"literature":[91],"estimation":[95],"from":[96,185],"RCTs":[97],"has":[98,197],"a":[99,170],"substantial":[100],"history,":[101],"contributes":[103],"deservedly":[104],"level":[107],"trust":[109],"researchers":[110],"practitioners":[112],"have":[113],"\"gold":[116],"standard\"":[117],"evaluation":[119],"practices.":[120],"Nevertheless,":[121],"particular":[124],"case":[125],"experiments,":[129],"remark":[131],"that":[132,140,145],"certain":[133],"critical":[134],"issues":[135],"remain.":[136],"Specifically,":[137],"assumptions":[139],"required":[142],"ascertain":[144],"yield":[147],"unbiased":[148],"estimates":[149],"effect,":[153],"seldom":[155],"met":[156],"practical":[158],"applications.":[159],"We":[160,192],"argue":[161],"that,":[162],"because":[163],"typically":[165],"learn":[166],"using":[167],"pooled":[168],"data,":[169],"lack":[171],"interference":[174],"cannot":[175],"guaranteed.":[177],"This":[178],"undermines":[179],"conclusions":[181],"draw":[184],"discuss":[193],"implications":[195],"for":[198,201],"practitioners,":[199],"research":[203],"literature.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}