{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01086634,0.002061601,0.001973762,0.004736834,0.0007636375,0.004374145,0.002143801,0.001711911,0.001716011],"category_scores_gemma":[0.03718445,0.0008567309,0.002258193,0.002830522,0.001089258,0.004420642,0.004548954,0.003318921,0.001393358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000681238,"about_ca_system_score_gemma":0.001629635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009608214,"about_ca_topic_score_gemma":0.0011743,"domain_scores_codex":[0.9952957,0.002073044,0.0004055741,0.0006624217,0.001281535,0.0002817849],"domain_scores_gemma":[0.9804549,0.009155662,0.001805487,0.005739899,0.002467523,0.000376594],"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":[0.001217357,0.001245821,0.03288788,0.0006184047,0.0008681348,0.0006304621,0.0007040595,0.2005033,0.03614851,0.02544624,0.01305943,0.6866704],"study_design_scores_gemma":[0.00001796735,0.00008474796,0.001398337,0.00003511093,0.00005566017,0.0001326784,0.00008388965,0.9609975,0.008113559,0.02717024,0.001885714,0.00002452761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03344265,0.0006115102,0.9609712,0.0009870523,0.0001078355,0.0001379821,0.0005536122,0.002414873,0.0007732455],"genre_scores_gemma":[0.5695071,0.000627038,0.4251813,0.0003704628,0.0002760153,0.0002358727,0.001921703,0.0004103584,0.001470094],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01086634,"threshold_uncertainty_score":0.0574674,"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."}}