{"id":"W2477917200","doi":"10.1109/cisti.2016.7521522","title":"The use of predictive analytics technology to detect credit card fraud in Canada","year":2016,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University of Edmonton","funders":"","keywords":"Vendor; Credit card; Balanced scorecard; Credit card fraud; Predictive analytics; Analytics; Business; Chargeback; Card security code; Computer security; Computer science; Finance; Data science; Marketing; Payment","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001301319,0.00006885942,0.0001085395,0.0001505185,0.00003287378,0.00002081458,0.001039732,0.00004337369,0.000002694215],"category_scores_gemma":[0.0004349065,0.00003807669,0.00001296256,0.0007042155,0.00005965527,0.0002077529,0.0002890606,0.00006383428,0.000003693407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003534256,"about_ca_system_score_gemma":0.000526651,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.180559,"about_ca_topic_score_gemma":0.6736188,"domain_scores_codex":[0.9991285,0.00003038772,0.0002252674,0.0002188552,0.0002023578,0.0001946351],"domain_scores_gemma":[0.9984962,0.0003090989,0.00007420959,0.0009406419,0.0001388626,0.00004101891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003323384,0.00002621049,0.04995483,0.000007537387,0.00005317228,0.00001878698,0.0001102169,0.0002091268,0.02062971,0.1225737,0.1466065,0.6597769],"study_design_scores_gemma":[0.000406144,0.0003182992,0.08626775,0.00009395741,0.000007717651,0.000009482084,0.0001135469,0.02868821,0.5934281,0.01200921,0.2782384,0.0004191635],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006491349,0.000009399684,0.9866296,0.0062212,0.00009947645,0.0001821549,0.00003929844,0.000119548,0.0002079487],"genre_scores_gemma":[0.9191405,0.00002987252,0.08035974,0.0002042884,0.000008722693,0.00003940582,4.760664e-7,0.000004403167,0.0002126196],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9126491,"threshold_uncertainty_score":0.8248977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02541023062364184,"score_gpt":0.2477191563498566,"score_spread":0.2223089257262147,"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."}}