{"id":"W4362725573","doi":"10.23977/acss.2023.070212","title":"Assessing the feasibility of machine learning-based modelling and prediction of credit fraud outcomes using hyperparameter tuning","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Credit card fraud; Undersampling; Machine learning; Credit card; Computer science; Random forest; AdaBoost; Artificial intelligence; Support vector machine; Hyperparameter; Feature selection; Naive Bayes classifier; Data mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001262346,0.0001228148,0.0003236381,0.0001755212,0.0001045266,0.0001378362,0.0003012276,0.00005214669,2.775976e-7],"category_scores_gemma":[0.00003998576,0.00008966669,0.00003307715,0.0004064127,0.0001039263,0.0009148742,0.0001593594,0.0001432138,1.284742e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002103631,"about_ca_system_score_gemma":0.00002501591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006626599,"about_ca_topic_score_gemma":0.000001452661,"domain_scores_codex":[0.9984803,0.0002681746,0.0005193344,0.0003300939,0.0002483703,0.0001537467],"domain_scores_gemma":[0.9984572,0.0007211526,0.0003429709,0.000353873,0.00009642949,0.00002839388],"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":[0.000003403692,0.00002369726,0.172175,0.0002121704,0.000009446885,0.000001462983,0.0003099636,0.8172401,0.001616253,0.0004803735,0.000003633947,0.007924437],"study_design_scores_gemma":[0.0001792535,0.00006561357,0.007063867,0.0002419576,0.000004388781,0.000003943844,0.00004250606,0.9911814,0.0005224313,0.0005668741,0.00005269538,0.00007508289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2129415,0.0010659,0.7854676,0.00003598091,0.0001945601,0.0001916325,0.000009640352,0.00008649076,0.000006778769],"genre_scores_gemma":[0.9384435,0.0001193397,0.06137018,0.00001600354,0.00002568428,0.00001021646,0.000006116852,0.000006858726,0.000002091098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.725502,"threshold_uncertainty_score":0.3656501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1135348121537195,"score_gpt":0.3510707992363098,"score_spread":0.2375359870825903,"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."}}