{"id":"W3186353005","doi":"10.1016/j.engappai.2023.106248","title":"Uncertainty-aware credit card fraud detection using deep learning","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Australian Research Council","keywords":"Computer science; Credit card fraud; Process (computing); Dropout (neural networks); Confusion matrix; Machine learning; Monte Carlo method; Artificial intelligence; Deep learning; Ensemble learning; Database transaction; Credit card; Data mining; Database","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":[0.001572798,0.0006240303,0.001083881,0.001472526,0.0004205325,0.001315019,0.001245047,0.0009342476,0.00109044],"category_scores_gemma":[0.004305244,0.0003330837,0.0004653018,0.00110821,0.0004004135,0.001763213,0.001610501,0.001444005,0.0003643251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008854615,"about_ca_system_score_gemma":0.001234597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003883043,"about_ca_topic_score_gemma":0.003772928,"domain_scores_codex":[0.9992033,0.0001607291,0.00004791678,0.0001392351,0.0002549317,0.0001940015],"domain_scores_gemma":[0.9983118,0.0007225851,0.0002391976,0.0001818263,0.0004361781,0.0001084337],"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":[0.0006775243,0.0008977759,0.02369626,0.0001216445,0.0001816308,0.0002239403,0.0001020011,0.2592173,0.008596715,0.008885388,0.01033492,0.6870649],"study_design_scores_gemma":[0.00000440506,0.00001714552,0.0006247067,0.000005328863,0.000007460019,0.00002331642,0.000009931199,0.9952273,0.001186497,0.002594224,0.0002951695,0.000004513938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2613802,0.001860091,0.7268146,0.002038379,0.0002874201,0.0001040331,0.0006130132,0.001580163,0.005322133],"genre_scores_gemma":[0.9637668,0.0002237781,0.03351952,0.0002038734,0.0001006997,0.00002303438,0.0003971752,0.00002098214,0.001744232],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003883043,"threshold_uncertainty_score":0.008317888,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03142392293625725,"score_gpt":0.2878609277436617,"score_spread":0.2564370048074044,"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."}}