{"id":"W4407421883","doi":"10.1016/j.bar.2025.101560","title":"Reprint of: The use of machine learning algorithms to predict financial statement fraud","year":2025,"lang":"en","type":"article","venue":"The British Accounting Review","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":true,"has_abstract":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Reprint; Statement (logic); Financial statement; Computer science; Machine learning; Algorithm; Artificial intelligence; Finance; Accounting; Economics; Political science; Law; Audit","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001777297,0.001450115,0.0008889905,0.00535438,0.0007868666,0.003229508,0.00118131,0.002286904,0.04484124],"category_scores_gemma":[0.02326466,0.0004218935,0.0007916074,0.005371954,0.001355364,0.001798204,0.0006348118,0.004045237,0.02337826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001244488,"about_ca_system_score_gemma":0.001144295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007435088,"about_ca_topic_score_gemma":0.01277705,"domain_scores_codex":[0.9981571,0.0003827885,0.0002925069,0.0002351061,0.0008401257,0.00009242471],"domain_scores_gemma":[0.9789262,0.01074771,0.001404144,0.001384866,0.006937641,0.0005994739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004040738,0.000009865465,0.0001991166,0.0001964996,0.00001530664,0.00003954927,0.0000107801,0.0001157065,0.0001034713,0.001411439,0.9812935,0.0165644],"study_design_scores_gemma":[0.00003009137,0.00006108192,0.005100233,0.0004535296,0.00003464372,0.0003375597,0.00004393687,0.0009183116,0.0004812393,0.003460917,0.9890541,0.00002428116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"editorial","genre_gemma":"empirical","genre_scores_codex":[0.001298265,0.05374476,0.005277114,0.09833496,0.7820382,0.00006973996,0.009735828,0.0008881742,0.04861296],"genre_scores_gemma":[0.03668129,0.05443156,0.005943554,0.05774629,0.458689,0.0001690007,0.006576424,0.0008581999,0.3789047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04484124,"threshold_uncertainty_score":0.1500089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02836881766134944,"score_gpt":0.2820477703300203,"score_spread":0.2536789526686708,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}