{"id":"W4384209454","doi":"10.1002/ail2.85","title":"Predicting mobile money transaction fraud using machine learning algorithms","year":2023,"lang":"en","type":"article","venue":"Applied AI Letters","topic":"Crime, Illicit Activities, and Governance","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Roads University","funders":"","keywords":"Money laundering; Database transaction; Random forest; Mobile payment; Financial transaction; Computer science; Logistic regression; Law enforcement; Classifier (UML); Transaction data; Artificial intelligence; Machine learning; Algorithm; Payment; Business; Finance; Database; Law; Political science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003795828,0.0001372929,0.0001648173,0.00008813468,0.0008885599,0.00009611093,0.000150516,0.0000890966,0.00008325054],"category_scores_gemma":[0.00002440263,0.0001533781,0.00007116923,0.0004830509,0.0001405284,0.0002429617,0.00001987594,0.0003665621,0.00007512852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001600252,"about_ca_system_score_gemma":0.00004135486,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01294031,"about_ca_topic_score_gemma":0.0007458057,"domain_scores_codex":[0.9985554,0.00006178628,0.0001730802,0.0002943307,0.0004542507,0.0004611175],"domain_scores_gemma":[0.999539,0.0001424089,0.0001089458,0.0001128778,0.00001602848,0.0000807349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001358049,0.000166546,0.02631987,0.000134475,0.0002377546,0.00007511855,0.1455775,0.1144355,0.5450866,0.002560179,0.008055265,0.1572154],"study_design_scores_gemma":[0.002566683,0.0001263646,0.0067737,0.0001600425,0.0002176164,0.000009089995,0.0495375,0.192971,0.03463256,0.000863354,0.7100251,0.002116994],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861768,0.00004591516,0.007867402,0.001443499,0.0004836163,0.0003183365,0.00001466863,0.0005358727,0.003113901],"genre_scores_gemma":[0.9970825,0.00008599347,0.000276236,0.001274696,0.0006386564,0.00005086459,0.00001450081,0.00003160157,0.000544973],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7019698,"threshold_uncertainty_score":0.9936326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02060281957099611,"score_gpt":0.2807653426111022,"score_spread":0.2601625230401061,"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."}}