{"id":"W3011219038","doi":"10.1109/ai4i46381.2019.00030","title":"Short Paper: Credit Card Fraud Detection using LightGBM with Asymmetric Error Control","year":2019,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Credit card; Credit card fraud; Computer science; Constant false alarm rate; False alarm; Confidentiality; Control (management); Error detection and correction; Computer security; Word error rate; Data mining; ALARM; Artificial intelligence; Algorithm; Engineering; 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":[0.004766209,0.0007636542,0.001162011,0.001827828,0.0009271615,0.002573843,0.001778111,0.001783589,0.00176097],"category_scores_gemma":[0.01588224,0.0002878842,0.000534959,0.001723341,0.001323801,0.002793733,0.002140992,0.001976904,0.001312259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001615148,"about_ca_system_score_gemma":0.001376084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001950474,"about_ca_topic_score_gemma":0.001354382,"domain_scores_codex":[0.9958339,0.001433981,0.0001862431,0.0005691361,0.001635407,0.0003413969],"domain_scores_gemma":[0.9918751,0.002637315,0.001004075,0.0023068,0.001813367,0.000363402],"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":[0.001277249,0.0004716105,0.01453232,0.0002329436,0.0002005672,0.0003521678,0.0003390483,0.07671504,0.02534826,0.02751828,0.01697788,0.8360346],"study_design_scores_gemma":[0.00002863389,0.0001128868,0.001823493,0.00003050115,0.00002672112,0.0002689809,0.00006651784,0.9676815,0.0143445,0.01118611,0.004398253,0.00003197618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06083411,0.0009022673,0.9323847,0.001389192,0.0005233254,0.0001625552,0.000165901,0.001319136,0.002318762],"genre_scores_gemma":[0.6860634,0.0004852333,0.3071379,0.0008029981,0.0005951087,0.0001048502,0.0003637993,0.0001373554,0.004309309],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004766209,"threshold_uncertainty_score":0.02520645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01558655689854913,"score_gpt":0.2456354857586418,"score_spread":0.2300489288600927,"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."}}