{"id":"W3186924568","doi":"10.1109/access.2021.3096799","title":"Intelligent Fraud Detection in Financial Statements Using Machine Learning and Data Mining: A Systematic Literature Review","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Audit; Cluster analysis; Anomaly detection; Unsupervised learning; Focus (optics); Key (lock); Machine learning; Heuristic; Finance; Artificial intelligence; Data mining; Data science; Accounting; Computer security; Business","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0006991263,0.0001167392,0.0002547683,0.0001208938,0.00007718636,0.0004644769,0.0009857827,0.00005098416,0.000003371126],"category_scores_gemma":[0.0005553522,0.0001090578,0.00001511764,0.0008796505,0.00001297686,0.001985278,0.0006972809,0.0002027644,0.000001962293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000600216,"about_ca_system_score_gemma":0.00006274406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001869101,"about_ca_topic_score_gemma":0.0000700424,"domain_scores_codex":[0.998485,0.0002548321,0.000421356,0.0004830255,0.0002019676,0.0001538717],"domain_scores_gemma":[0.9987595,0.00006807246,0.0002264226,0.000800473,0.0001078948,0.00003762935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005027125,0.000809279,0.02566748,0.4508148,0.0001880035,0.001644726,0.00533436,0.0001841157,0.06130847,0.001890161,0.003154974,0.4489534],"study_design_scores_gemma":[0.0005590389,0.00007974231,0.001373262,0.1734722,0.00008383441,0.0003872548,0.00005276944,0.7068633,0.1099217,0.0007680224,0.00556264,0.0008761898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007610324,0.03903184,0.9522516,0.0001601017,0.0002938123,0.0004857101,0.00002404213,0.000121203,0.0000214312],"genre_scores_gemma":[0.7857246,0.08723909,0.1241367,0.001971164,0.000142161,0.0001884745,0.0003780052,0.00004572705,0.0001740722],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8281148,"threshold_uncertainty_score":0.4478962,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09531188645907628,"score_gpt":0.4084828426708726,"score_spread":0.3131709562117964,"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."}}