{"id":"W4394853018","doi":"10.1080/2573234x.2024.2342773","title":"Predicting fraud in MD&A sections using deep learning","year":2024,"lang":"en","type":"article","venue":"Journal of Business Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Convolutional neural network; Transformer; F1 score; Machine learning; Artificial neural network; Engineering","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":[0.0006895593,0.0001004526,0.0001946605,0.000747348,0.00008874601,0.000382583,0.0004666158,0.00006853246,0.000008398485],"category_scores_gemma":[0.0003619021,0.00009140393,0.00006730853,0.002257273,0.00002860883,0.001199972,0.0001101256,0.0005044914,0.000005593388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002061732,"about_ca_system_score_gemma":0.0001931714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002861967,"about_ca_topic_score_gemma":0.00002409176,"domain_scores_codex":[0.9987495,0.00005513017,0.0005396617,0.000163861,0.0003177717,0.0001740526],"domain_scores_gemma":[0.9988765,0.0001215523,0.0002851011,0.0002286051,0.0004366993,0.00005157637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002628756,0.0003884055,0.09509625,0.0005720734,0.0003165676,0.0007742376,0.003649982,0.6908972,0.03975774,0.02443806,0.002100542,0.1419826],"study_design_scores_gemma":[0.00009756158,0.00001963782,0.008923451,0.0003813226,0.00002936257,0.0003599591,0.00006988055,0.9771221,0.0004866364,0.001434813,0.01094833,0.0001269578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03333176,0.0006316868,0.9647752,0.0004280501,0.0004986877,0.00003418405,9.964962e-7,0.0001054297,0.0001940042],"genre_scores_gemma":[0.8709901,0.0003828199,0.1282156,0.00004213308,0.0002709068,8.836591e-7,0.00000179783,0.00001496318,0.00008085639],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8376583,"threshold_uncertainty_score":0.3727344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04788753852339553,"score_gpt":0.3088563643410194,"score_spread":0.2609688258176238,"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."}}