{"id":"https://openalex.org/W4400919790","doi":"https://doi.org/10.1145/3676188","title":"Is Model Accuracy Enough? A Field Evaluation of a Machine Learning Model to Catch Bogus Firms","display_name":"Is Model Accuracy Enough? A Field Evaluation of a Machine Learning Model to Catch Bogus Firms","publication_year":2024,"publication_date":"2024-07-23","ids":{"openalex":"https://openalex.org/W4400919790","doi":"https://doi.org/10.1145/3676188"},"language":"en","primary_location":{"id":"doi:10.1145/3676188","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676188","pdf_url":null,"source":{"id":"https://openalex.org/S4387291547","display_name":"ACM Journal on Computing and Sustainable Societies","issn_l":"2834-5533","issn":["2834-5533"],"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 Journal on Computing and Sustainable Societies","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/A5104973288","display_name":"Taha Barwahwala","orcid":"https://orcid.org/0009-0003-8153-947X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Taha Barwahwala","raw_affiliation_strings":["Columbia University, New York, United States"],"affiliations":[{"raw_affiliation_string":"Columbia University, New York, United States","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081632162","display_name":"Aprajit Mahajan","orcid":"https://orcid.org/0000-0001-9448-180X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aprajit Mahajan","raw_affiliation_strings":["Agricultural and Resource Economics, University of California Berkeley, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"Agricultural and Resource Economics, University of California Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067841460","display_name":"Shekhar Mittal","orcid":"https://orcid.org/0009-0007-4197-0782"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shekhar Mittal","raw_affiliation_strings":["Amazon.com Inc, Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon.com Inc, Seattle, United States","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016161940","display_name":"Ofir Reich","orcid":"https://orcid.org/0000-0002-3727-9354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ofir Reich","raw_affiliation_strings":["Independent Data Scientist, Tel Aviv, Israel"],"affiliations":[{"raw_affiliation_string":"Independent Data Scientist, Tel Aviv, Israel","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104973288"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16645275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":"3","first_page":"1","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9846000075340271,"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"}},"topics":[{"id":"https://openalex.org/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.9846000075340271,"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"}},{"id":"https://openalex.org/T11838","display_name":"Crime, Illicit Activities, and Governance","score":0.9728999733924866,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10270","display_name":"Blockchain Technology Applications and Security","score":0.961899995803833,"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/computer-science","display_name":"Computer science","score":0.3912528455257416},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3791370391845703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35980141162872314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3912528455257416},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3791370391845703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35980141162872314}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676188","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3676188","pdf_url":null,"source":{"id":"https://openalex.org/S4387291547","display_name":"ACM Journal on Computing and Sustainable Societies","issn_l":"2834-5533","issn":["2834-5533"],"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 Journal on Computing and Sustainable Societies","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2809467077","https://openalex.org/W2951317862","https://openalex.org/W2966819520","https://openalex.org/W3005990175","https://openalex.org/W3087802397","https://openalex.org/W4210937926","https://openalex.org/W4223589472","https://openalex.org/W4226269366","https://openalex.org/W4285808017","https://openalex.org/W4311940024","https://openalex.org/W4385800084"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"We":[0,44,64,127],"investigate":[1],"the":[2,47,61,67,93,100,118,140,153,167,193],"use":[3,46],"of":[4,25,55,87,96,120,139,169,177,196],"a":[5,22,83,110,136,163],"machine":[6,170],"learning":[7,171],"(ML)":[8],"algorithm":[9],"to":[10,40,50,146],"identify":[11],"fraudulent":[12,42,121],"non-existent":[13,80],"firms":[14,56,88],"that":[15,66],"are":[16,189],"used":[17],"for":[18,131,166],"tax":[19,26,125,141],"evasion.":[20],"Using":[21],"rich":[23],"dataset":[24],"returns":[27],"in":[28,72,78,113,151,172,191],"an":[29,37,184],"Indian":[30],"state":[31],"over":[32],"several":[33],"years,":[34],"we":[35,91],"train":[36],"ML-based":[38],"model":[39,48,69,154],"predict":[41],"firms.":[43,81],"then":[45],"predictions":[49],"carry":[51],"out":[52],"field":[53,76],"inspections":[54,106],"identified":[57],"as":[58,115,162,183],"suspicious":[59],"by":[60,117],"ML":[62,68],"tool.":[63],"find":[65],"is":[70],"accurate":[71],"both":[73],"simulated":[74],"and":[75,124,148,176],"settings":[77],"identifying":[79],"Withholding":[82],"randomly":[84],"selected":[85],"group":[86],"from":[89],"inspection,":[90],"estimate":[92],"causal":[94],"impact":[95,195],"ML-driven":[97],"inspections.":[98],"Despite":[99],"strong":[101],"predictive":[102,197],"performance,":[103],"our":[104],"model-driven":[105],"do":[107],"not":[108],"yield":[109],"significant":[111],"increase":[112],"enforcement":[114],"evidenced":[116],"cancellation":[119],"firm":[122],"registrations":[123],"recovery.":[126],"provide":[128],"two":[129],"explanations":[130],"this":[132],"discrepancy":[133],"based":[134],"on":[135,180],"close":[137],"analysis":[138],"department\u2019s":[142],"operating":[143],"protocols:":[144],"overfitting":[145],"proxy-labels":[147],"institutional":[149],"friction":[150],"integrating":[152],"into":[155],"existing":[156],"administrative":[157],"systems.":[158],"Our":[159],"study":[160],"serves":[161],"cautionary":[164],"tale":[165],"application":[168],"public":[173],"policy":[174],"contexts":[175],"relying":[178],"solely":[179],"test-set":[181],"performance":[182],"effectiveness":[185],"indicator.":[186],"Field":[187],"evaluations":[188],"critical":[190],"assessing":[192],"real-world":[194],"models.":[198]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2024-07-24T00:00:00"}