{"id":"W2967845527","doi":"10.1108/ajar-09-2018-0032","title":"Detecting anomalies in financial statements using machine learning algorithm","year":2019,"lang":"en","type":"article","venue":"Asian Journal of Accounting Research","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Roads University","funders":"","keywords":"Anomaly detection; Finance; Econometrics; Computer science; Actuarial science; Data mining; Accounting; Business; Economics","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":[],"consensus_categories":[],"category_scores_codex":[0.004135385,0.0001680292,0.0003248512,0.001316528,0.0003430033,0.0005337556,0.0003846298,0.0001025447,0.0001848951],"category_scores_gemma":[0.0009413277,0.0001580076,0.000105671,0.001278994,0.00005853423,0.002896235,0.0002451671,0.001181103,0.00008004512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001585075,"about_ca_system_score_gemma":0.0001326992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001030207,"about_ca_topic_score_gemma":0.0001630776,"domain_scores_codex":[0.997368,0.00006976031,0.000715223,0.0002406092,0.0009710598,0.0006353105],"domain_scores_gemma":[0.9984633,0.00006956555,0.0005836732,0.0001354834,0.0007284257,0.00001949427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001621244,0.0001211366,0.837602,0.0002619911,0.00002314686,0.0001635155,0.0002655658,0.0007314148,0.003923482,0.0004408285,0.000112725,0.1561921],"study_design_scores_gemma":[0.005784343,0.0004229626,0.6623404,0.002944236,0.00007215755,0.0001176605,0.007556168,0.2798739,0.0009327388,0.006142402,0.03280102,0.00101197],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953438,0.0001962746,0.0006487439,0.0001717365,0.0006496898,0.0001884723,0.000002205774,0.00002102924,0.002778042],"genre_scores_gemma":[0.9972948,0.00001562581,0.00108289,0.00005384703,0.00142274,0.000002053041,0.000005373559,0.00003398802,0.00008865575],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2791425,"threshold_uncertainty_score":0.6443363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03589708034145628,"score_gpt":0.3285269592834637,"score_spread":0.2926298789420074,"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."}}