{"id":"W4415649477","doi":"10.3390/jrfm18110605","title":"Using Machine Learning to Detect Financial Statement Fraud: A Cross-Country Analysis Applied to Wirecard AG","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Financial statement; Vendor; Pipeline (software); Boosting (machine learning); Gradient boosting; Statement (logic); Ensemble learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00695175,0.0009107222,0.0008166871,0.003753844,0.0004996244,0.001300721,0.000573633,0.0008843628,0.0006426209],"category_scores_gemma":[0.01132206,0.0002435886,0.00130853,0.001997736,0.000577372,0.00129594,0.001078832,0.001259675,0.0003964055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008443889,"about_ca_system_score_gemma":0.0004081727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007932747,"about_ca_topic_score_gemma":0.004647125,"domain_scores_codex":[0.9968417,0.001830159,0.0001829654,0.0004346602,0.0004367299,0.0002737893],"domain_scores_gemma":[0.9904357,0.005547832,0.001323837,0.001122589,0.001289214,0.0002809181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001182738,0.001531522,0.849027,0.0001084014,0.001226425,0.0004338914,0.0002028231,0.08824646,0.001642182,0.0008119651,0.003224541,0.05236218],"study_design_scores_gemma":[0.0001002134,0.001386094,0.4671074,0.0000828566,0.0005019548,0.0004801475,0.0008431513,0.5216191,0.004826171,0.0008810695,0.002110092,0.00006158918],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954284,0.0003462709,0.003085119,0.0001272854,0.00003123901,0.00003257656,0.0003983232,0.00003536389,0.0005155118],"genre_scores_gemma":[0.9962344,0.0001063999,0.002367055,0.00003315684,0.00001936326,0.00001459824,0.0009977802,0.000009104228,0.0002182187],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007932747,"threshold_uncertainty_score":0.0367648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01047184739881426,"score_gpt":0.2840781956072661,"score_spread":0.2736063482084519,"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."}}