{"id":"W4383560185","doi":"10.54254/2755-2721/4/2023333","title":"Impact of different transaction features on credit card fraud detection by neural networks","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Credit card fraud; Credit card; Database transaction; Feature (linguistics); Computer science; Artificial neural network; Transaction data; Chargeback; ATM card; Card security code; Machine learning; Artificial intelligence; Data mining; Database; Payment; World Wide Web","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":[0.003961459,0.0009830719,0.000789108,0.001409272,0.0005622676,0.001504779,0.0005829839,0.000846913,0.0005146078],"category_scores_gemma":[0.01376695,0.0002812741,0.0005840846,0.001011193,0.0005515834,0.002261688,0.0008904485,0.001008598,0.0001873269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001269105,"about_ca_system_score_gemma":0.0006699983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009539942,"about_ca_topic_score_gemma":0.005468974,"domain_scores_codex":[0.9983742,0.000543672,0.0001692561,0.0002421055,0.0004419345,0.0002288841],"domain_scores_gemma":[0.9944036,0.003718941,0.0005602625,0.000374775,0.0008041156,0.0001384091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00193514,0.0008664944,0.1157301,0.000124762,0.0002896047,0.0003419805,0.0001808181,0.5893973,0.005340219,0.001043485,0.001784401,0.2829657],"study_design_scores_gemma":[0.000007279633,0.00008062013,0.005694873,0.00001238709,0.00002942903,0.00003142414,0.00004225129,0.9913374,0.002252565,0.0003729476,0.0001288392,0.000009969513],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9736015,0.0009836336,0.02254121,0.0005292535,0.0001134034,0.00003294469,0.0001416549,0.000214171,0.001842312],"genre_scores_gemma":[0.9956923,0.0001500597,0.003696465,0.00003412328,0.00001611067,0.00000800511,0.0001207727,0.000006824512,0.0002752838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009539942,"threshold_uncertainty_score":0.02095044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006430267088186143,"score_gpt":0.2208888503312842,"score_spread":0.214458583243098,"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."}}