{"id":"W4416873823","doi":"10.1109/inc465408.2025.11256487","title":"Fraudulent Firm Classification in External Financial Audits using Machine Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Optech (Canada)","funders":"","keywords":"C4.5 algorithm; Audit; Big data; Interpretability; Naive Bayes classifier; Feature selection; Particle swarm optimization; Scalability; Feature (linguistics)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001186119,0.0004275021,0.0004641202,0.0009277778,0.0004183498,0.0004903657,0.001726883,0.0003663571,0.0001889957],"category_scores_gemma":[0.00066031,0.0004738988,0.0001236319,0.002278253,0.000161791,0.001217777,0.0008464681,0.001063754,0.0000865792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008164876,"about_ca_system_score_gemma":0.0008373982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005655171,"about_ca_topic_score_gemma":0.0001864837,"domain_scores_codex":[0.9958184,0.0004225429,0.001229089,0.00127248,0.0005510231,0.0007065147],"domain_scores_gemma":[0.9977018,0.0001687089,0.0005261271,0.001224907,0.0002637629,0.0001146418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008319941,0.0007281509,0.08210785,0.0002025415,0.00002284395,0.00003474929,0.0006346249,0.001068833,0.05860213,0.440672,0.001785798,0.4140572],"study_design_scores_gemma":[0.000550535,0.00006391605,0.1323939,0.0005343203,0.00001367875,0.00000691611,0.00002293664,0.83535,0.01414805,0.00553482,0.01098853,0.0003924136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01593971,0.0009807791,0.975639,0.001901749,0.001126254,0.0006109481,0.00001570318,0.0003691438,0.003416755],"genre_scores_gemma":[0.8121721,0.000383372,0.1832967,0.0007211698,0.0001128708,0.00005558781,0.00002516515,0.00001969174,0.003213366],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8342811,"threshold_uncertainty_score":0.9997713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03753821989105183,"score_gpt":0.307735224475259,"score_spread":0.2701970045842071,"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."}}