{"id":"W4395018386","doi":"10.1109/icosst60641.2023.10505068","title":"Overcoming Imbalanced Datasets and Feature Complexity in Fraud Transaction Detection Through Down-Sampling and Dimension Reduction","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bishop's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Database transaction; Reduction (mathematics); Dimension (graph theory); Dimensionality reduction; Feature (linguistics); Data mining; Sampling (signal processing); Pattern recognition (psychology); Artificial intelligence; Mathematics; Database; Detector","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003371114,0.0001314649,0.0001473272,0.000175087,0.0001883671,0.0001323241,0.0001587906,0.0001100085,0.000002521231],"category_scores_gemma":[0.00002856202,0.0001283292,0.0000149201,0.0006663825,0.00006445558,0.001535887,0.00010676,0.0002126366,0.00000505797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006707422,"about_ca_system_score_gemma":0.00001051262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002061877,"about_ca_topic_score_gemma":0.000116319,"domain_scores_codex":[0.9988529,0.00006692048,0.0001895772,0.0005205757,0.0001659359,0.0002041081],"domain_scores_gemma":[0.999398,0.00006081439,0.00007795119,0.0003976988,0.00002588031,0.00003967146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006786137,0.00006402606,0.001111325,0.0001047473,0.00001448182,0.00000657155,0.0015741,0.0001242579,0.8083485,0.0127152,0.001774802,0.1740942],"study_design_scores_gemma":[0.001482047,0.0001662514,0.3065244,0.0001796922,0.00001484655,0.0001949354,0.0004751519,0.2747775,0.372893,0.03610465,0.006421392,0.0007660585],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1937877,0.00004655652,0.8036423,0.001199684,0.0002062371,0.0002859721,0.00003601368,0.0007237719,0.00007176845],"genre_scores_gemma":[0.906718,0.000274885,0.09267674,0.00007930295,0.00002615197,0.00002457941,0.0001683662,0.000008254515,0.00002368042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7129303,"threshold_uncertainty_score":0.5233114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06048644076122597,"score_gpt":0.3133627878569141,"score_spread":0.2528763470956881,"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."}}