{"id":"W4405411700","doi":"10.21203/rs.3.rs-5635767/v1","title":"Harnessing Exploratory Data Analysis for Robust Financial Fraud Detection and Model Enhancement","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Business; Exploratory analysis; Finance; Computer science; Data science","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":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.003044848,0.0002392768,0.0003517013,0.00118214,0.0004056123,0.001275502,0.002516725,0.0003035305,0.000003866809],"category_scores_gemma":[0.0004936107,0.0002402481,0.0001025432,0.001362194,0.0001321088,0.0006084276,0.01017843,0.001130058,0.00001165476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000322756,"about_ca_system_score_gemma":0.0008562722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004744683,"about_ca_topic_score_gemma":0.0000932781,"domain_scores_codex":[0.9961457,0.0002389973,0.0003972268,0.001802113,0.00091849,0.000497431],"domain_scores_gemma":[0.9955206,0.0002108535,0.0001329496,0.00339065,0.0006151876,0.0001297636],"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":[0.0001564637,0.0006129454,0.000269984,0.01040318,0.00113251,0.00004942305,0.004247592,0.03316188,0.02363208,0.04940425,0.03870865,0.8382211],"study_design_scores_gemma":[0.00007369065,0.00004494609,0.0001497198,0.0002532755,0.00005752129,5.190983e-7,0.00004221609,0.9586031,0.009356992,0.0299018,0.001283572,0.0002326856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001095685,0.001120852,0.994856,0.0006254594,0.0001981617,0.001037122,0.0005895989,0.0003603008,0.0001168192],"genre_scores_gemma":[0.6133345,0.0006466417,0.3824465,0.0000420418,0.0002535369,0.001868815,0.0009856875,0.00004148947,0.0003807945],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9254412,"threshold_uncertainty_score":0.9997613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2260434733925498,"score_gpt":0.4210172000216969,"score_spread":0.1949737266291471,"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."}}