{"id":"W4390738572","doi":"10.1109/tbdata.2024.3352978","title":"GAT-COBO: Cost-Sensitive Graph Neural Network for Telecom Fraud Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Computer science; Graph; Artificial intelligence; Machine learning; Classifier (UML); Theoretical computer 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":[0.0003915016,0.0002143661,0.0001753168,0.0002646081,0.0003490393,0.0003856299,0.001308265,0.0001267414,0.000006462057],"category_scores_gemma":[0.00001448026,0.0002130798,0.00009437205,0.001013141,0.00007255888,0.001173625,0.00001626168,0.00037338,0.00007310741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008280561,"about_ca_system_score_gemma":0.00007886802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000461642,"about_ca_topic_score_gemma":0.0002134873,"domain_scores_codex":[0.9980821,0.0000834852,0.0002994683,0.0009120636,0.0002448597,0.0003780506],"domain_scores_gemma":[0.9973955,0.0003616555,0.0000631058,0.001989299,0.00009511315,0.00009535787],"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":[0.00002979533,0.0000626462,8.772533e-7,0.00002784666,0.00005129737,0.000007832376,0.00005550449,0.001336434,0.003818099,0.0007271854,0.01523815,0.9786443],"study_design_scores_gemma":[0.0003000008,0.000232079,0.0001403172,0.00009530546,0.00005898368,0.00006940705,0.00001515691,0.7492533,0.1401845,0.00229992,0.1068963,0.0004546994],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001398447,0.00007453575,0.9908367,0.001033497,0.004058778,0.0007240314,0.001690562,0.001370966,0.00007102542],"genre_scores_gemma":[0.9323689,0.0001585227,0.06554344,0.0005824468,0.0004305242,0.0003317015,0.000340656,0.0000419979,0.0002018037],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9781896,"threshold_uncertainty_score":0.8689142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08922606455742202,"score_gpt":0.3055968200315244,"score_spread":0.2163707554741024,"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."}}