{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001155185,0.0001782806,0.000395694,0.001082908,0.0002935051,0.0003005401,0.0006444705,0.00005901806,0.000004282422],"category_scores_gemma":[0.0001713502,0.0001673712,0.0001100062,0.002006553,0.00002596475,0.0002552241,0.0005417525,0.00027413,0.000004372235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002010871,"about_ca_system_score_gemma":0.00008152061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008043149,"about_ca_topic_score_gemma":0.00005784387,"domain_scores_codex":[0.9982474,0.00005825246,0.0006707294,0.0003533179,0.0003892519,0.0002810618],"domain_scores_gemma":[0.9989269,0.00004310936,0.0003961366,0.0003607023,0.0001575769,0.0001155938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002799503,0.00009455085,0.01967385,0.00007565628,0.0002153165,0.00006552383,0.0009359118,0.0303148,0.0006455452,0.02512618,0.001720661,0.9208521],"study_design_scores_gemma":[0.001724334,0.0005748449,0.4559209,0.0002357962,0.0008438455,0.000008858457,0.0001157705,0.02006739,0.003622331,0.01206074,0.5040402,0.0007849612],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06413889,0.0001479591,0.9347404,0.0001213418,0.0002352734,0.0002735861,0.00001755678,0.000045488,0.0002795488],"genre_scores_gemma":[0.6821275,0.0003280504,0.3165417,0.0007732035,0.00008169915,0.00002098159,0.000003104527,0.000007855995,0.0001158839],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9200671,"threshold_uncertainty_score":0.68252,"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."}}