{"id":"W4404983478","doi":"10.21203/rs.3.rs-5147684/v1","title":"Optimized Feature Selection and Enhanced Recurrent Neural Network for Financial Fraud Detection","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Database transaction; Feature selection; Credit card fraud; Financial fraud; Financial statement; Selection (genetic algorithm); Financial transaction; Artificial neural network; Artificial intelligence; Feature (linguistics); Machine learning; Credit card; Finance; Data mining; Business; Accounting; Payment; Database","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00175783,0.0002872947,0.0003331858,0.0004375028,0.0004334807,0.0008682265,0.0008783634,0.0005744945,0.000004756738],"category_scores_gemma":[0.0006686669,0.0002787321,0.0001397736,0.0009815764,0.00007739192,0.0002233362,0.002070799,0.002444877,0.00001268162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003809522,"about_ca_system_score_gemma":0.0004045785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002741894,"about_ca_topic_score_gemma":0.00005442775,"domain_scores_codex":[0.996625,0.0004021112,0.0003025033,0.001296786,0.0006851412,0.0006884529],"domain_scores_gemma":[0.9977803,0.0003463704,0.0001350377,0.000826694,0.0007728681,0.0001387138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000384083,0.0001163436,0.00002077178,0.002854211,0.00006359662,0.000008292545,0.0006034385,0.002848801,0.006956549,0.02304415,0.1027933,0.8603065],"study_design_scores_gemma":[0.0005788495,0.0007494622,0.001383983,0.001211146,0.00002251798,0.00001467211,0.00001949931,0.8113044,0.0392567,0.123596,0.02118895,0.0006738477],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004148998,0.00158723,0.9861711,0.002279866,0.001619332,0.002937187,0.0001356403,0.0009755304,0.0001451361],"genre_scores_gemma":[0.6139143,0.001320768,0.3750694,0.00009061566,0.002572419,0.005681088,0.0004125999,0.00009238395,0.0008463872],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8596326,"threshold_uncertainty_score":0.9999665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04594276553995769,"score_gpt":0.3785044553629356,"score_spread":0.332561689822978,"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."}}