{"id":"W4413394506","doi":"10.1109/iaecst64597.2024.11117868","title":"Telecom Fraud Detection Based on Deep Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Telecommunications; Computer science; Deep learning; Computer security; Artificial intelligence","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":[0.0002014506,0.00007415061,0.00005266885,0.0001755877,0.00008020023,0.0002746666,0.0003514256,0.00004680661,0.00006827493],"category_scores_gemma":[0.00005179233,0.0000643956,0.00003074696,0.0004368881,0.00001223452,0.0003383445,0.0000469588,0.0002010288,0.000427865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006272564,"about_ca_system_score_gemma":0.00002222877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007340012,"about_ca_topic_score_gemma":0.000004731187,"domain_scores_codex":[0.9992455,0.00004436771,0.0001053727,0.0003095767,0.000165702,0.000129535],"domain_scores_gemma":[0.9994349,0.0001139309,0.00001940234,0.0003724162,0.00002658957,0.00003269262],"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":[0.000001808501,0.00001857097,0.00005194339,0.00001329835,0.000003140771,0.000006356531,0.00004271929,0.0003693375,0.009757008,0.04540614,0.001204142,0.9431255],"study_design_scores_gemma":[0.00002801026,0.00007151673,0.0005120318,0.00001350132,8.811843e-7,0.000002259886,0.000003026989,0.8392748,0.09755477,0.001057814,0.06140093,0.00008043001],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001786567,0.00002350026,0.980465,0.0007353917,0.000219544,0.0000710138,3.617175e-7,0.002776762,0.0155298],"genre_scores_gemma":[0.9088756,0.000005062135,0.08989314,0.0004338456,0.00003713939,0.00002666832,0.000004161895,0.00000831992,0.0007160901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9430451,"threshold_uncertainty_score":0.5499482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01005799193352516,"score_gpt":0.2477298961950716,"score_spread":0.2376719042615464,"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."}}