{"id":"https://openalex.org/W4416232957","doi":"https://doi.org/10.1145/3768292.3770372","title":"Financial Statement Fraud Detection with a Categorical-to-Numerical Data Representation","display_name":"Financial Statement Fraud Detection with a Categorical-to-Numerical Data Representation","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416232957","doi":"https://doi.org/10.1145/3768292.3770372"},"language":"en","primary_location":{"id":"doi:10.1145/3768292.3770372","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768292.3770372","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3768292.3770372","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120353185","display_name":"Tuna Alaygut","orcid":"https://orcid.org/0009-0009-8119-3740"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Tuna Alaygut","raw_affiliation_strings":["Artificial Intelligence and Data Engineering, Ozyegin University, Istanbul, Select State, Turkiye"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Data Engineering, Ozyegin University, Istanbul, Select State, Turkiye","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005523015","display_name":"Emre Sefer","orcid":"https://orcid.org/0000-0002-9186-0270"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Emre Sefer","raw_affiliation_strings":["Artificial Intelligence and Data Engineering, Ozyegin University, Istanbul, Select State, Turkiye"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Data Engineering, Ozyegin University, Istanbul, Select State, Turkiye","institution_ids":["https://openalex.org/I44925452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120353185"],"corresponding_institution_ids":["https://openalex.org/I44925452"],"apc_list":null,"apc_paid":null,"fwci":7.3194,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97050652,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.3111000061035156,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.3111000061035156,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.3019999861717224,"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/T10081","display_name":"Auditing, Earnings Management, Governance","score":0.08340000361204147,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.9521999955177307},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5217999815940857},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48980000615119934},{"id":"https://openalex.org/keywords/financial-statement","display_name":"Financial statement","score":0.4632999897003174},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/statement","display_name":"Statement (logic)","score":0.4237000048160553},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4018999934196472},{"id":"https://openalex.org/keywords/transitive-relation","display_name":"Transitive relation","score":0.39890000224113464}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.9521999955177307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6173999905586243},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5217999815940857},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C2781027943","wikidata":"https://www.wikidata.org/wiki/Q192907","display_name":"Financial statement","level":3,"score":0.4632999897003174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C2777026412","wikidata":"https://www.wikidata.org/wiki/Q2684591","display_name":"Statement (logic)","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4018999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39910000562667847},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C2776743756","wikidata":"https://www.wikidata.org/wiki/Q5097921","display_name":"Safeguarding","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33640000224113464},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3768292.3770372","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768292.3770372","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},{"id":"pmh:oai:eresearch.ozyegin.edu.tr:10679/11260","is_oa":true,"landing_page_url":"https://hdl.handle.net/10679/11260","pdf_url":null,"source":{"id":"https://openalex.org/S4306400232","display_name":"ECS Journal of Solid State Science and Technology (The Electrochemical Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802273670","host_organization_name":"Electrochemical Society","host_organization_lineage":["https://openalex.org/I2802273670"],"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":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3768292.3770372","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768292.3770372","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8201378633","display_name":null,"funder_award_id":"2224-A","funder_id":"https://openalex.org/F4320322626","funder_display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu"}],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1963859450","https://openalex.org/W1986584632","https://openalex.org/W2040870580","https://openalex.org/W2096945460","https://openalex.org/W2132966115","https://openalex.org/W2177569465","https://openalex.org/W2295598076","https://openalex.org/W2399473281","https://openalex.org/W2517540742","https://openalex.org/W2765449478","https://openalex.org/W2811024573","https://openalex.org/W2897138744","https://openalex.org/W2898085636","https://openalex.org/W2964182926","https://openalex.org/W3093945404","https://openalex.org/W3111640100","https://openalex.org/W3116035679","https://openalex.org/W3125433491","https://openalex.org/W3153858161","https://openalex.org/W3169936356","https://openalex.org/W3174086521","https://openalex.org/W3184584113","https://openalex.org/W3197759119","https://openalex.org/W4223578108","https://openalex.org/W4313201048","https://openalex.org/W4321592872","https://openalex.org/W4382469817","https://openalex.org/W4386815495","https://openalex.org/W4391483046","https://openalex.org/W4406148206","https://openalex.org/W4407414774","https://openalex.org/W4409983230"],"related_works":[],"abstract_inverted_index":{"Identifying":[0],"fraudulent":[1],"financial":[2,66,87],"reports":[3],"and":[4,31,100,122,152,165,185,191],"elucidating":[5],"the":[6,65,74,161,180,195],"mechanisms":[7],"of":[8,163],"fraud":[9,68,89,197],"are":[10,83,143],"critical":[11],"for":[12,76,86],"safeguarding":[13],"investors":[14],"from":[15],"substantial":[16],"losses.":[17],"Financial":[18],"statements":[19],"present":[20],"detailed":[21],"accounting":[22,36],"entries":[23],"in":[24,63,176],"tabular":[25],"form;":[26],"they":[27],"inherently":[28],"combine":[29],"categorical":[30,55,78,134],"numerical":[32,59,80],"variables":[33,56,60],"governed":[34],"by":[35],"dependencies,":[37],"yet":[38],"most":[39],"existing":[40],"methods":[41,75,128],"fail":[42],"to":[43,79],"model":[44],"interpretable":[45,192],"interactions":[46],"between":[47],"these":[48],"feature":[49],"types.":[50],"In":[51],"this":[52],"case,":[53],"handling":[54],"together":[57,167],"with":[58,110],"is":[61],"important":[62],"enhancing":[64],"statement":[67,88],"detection":[69],"performance.":[70],"Here,":[71],"we":[72],"compare":[73,103],"transforming":[77],"attributes,":[81],"which":[82],"then":[84],"used":[85],"detection.":[90],"We":[91,102],"perform":[92],"comprehensive":[93],"experiments":[94],"on":[95,133],"two":[96],"real-world":[97],"datasets:":[98],"FiGraph":[99],"USFSD.":[101],"4":[104],"state-of-the-art":[105,170],"specialized":[106,140],"categorical-to-numerical":[107],"transformation":[108,141],"techniques":[109,142],"several":[111],"other":[112],"simpler":[113],"statistical":[114],"encoding":[115],"mechanisms,":[116],"such":[117,136],"as":[118,125,127,137],"target,":[119],"label,":[120],"Helmert,":[121],"GLMM":[123],"encodings,":[124],"well":[126],"that":[129,160],"can":[130],"directly":[131],"work":[132],"data,":[135],"CatBoost.":[138],"These":[139],"Hierarchical":[144],"Coupling":[145],"Learning-based":[146,155],"CURE,":[147],"Graph-based":[148],"Categorical":[149],"Embedding":[150],"GCE,":[151],"Transitive":[153],"Distance":[154],"embedding.":[156],"The":[157],"results":[158],"reveal":[159],"performance":[162],"CURE":[164],"XGBoost":[166],"surpasses":[168],"all":[169],"techniques,":[171],"achieving":[172],"significant":[173],"relative":[174],"gains":[175],"macro-level":[177],"recall":[178],"over":[179],"second-best":[181],"performing":[182],"approaches,":[183],"CatBoost":[184],"FTTransformer,":[186],"while":[187],"also":[188],"providing":[189],"clear":[190],"insights":[193],"into":[194],"discovered":[196],"pathways.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-14T00:00:00"}