{"id":"W4404460773","doi":"10.9734/ajeba/2024/v24i111572","title":"Transforming Tax Compliance with Machine Learning: Reducing Fraud and Enhancing Revenue Collection","year":2024,"lang":"en","type":"article","venue":"Asian Journal of Economics Business and Accounting","topic":"Taxation and Compliance Studies","field":"Economics, Econometrics and Finance","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Independent Electricity System Operator","funders":"","keywords":"Compliance (psychology); Revenue; Business; Tax revenue; Data collection; Computer science; Accounting; Public economics; Economics; Psychology; Social psychology; Statistics; Mathematics","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":[0.0004680529,0.0001347598,0.0003632384,0.0002448834,0.0002456062,0.0003380819,0.00006745846,0.00004169123,0.00002142183],"category_scores_gemma":[0.00006120321,0.0001344768,0.0000423438,0.0002441538,0.00005327208,0.000754166,0.00002182982,0.0002411016,0.00000522552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005394294,"about_ca_system_score_gemma":0.00003465224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008066868,"about_ca_topic_score_gemma":0.0001368469,"domain_scores_codex":[0.999039,0.000006401162,0.0005496251,0.0002202886,0.00001760083,0.0001671011],"domain_scores_gemma":[0.9992658,0.00003516037,0.0005263946,0.00005650934,0.0000728456,0.00004321297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005281597,0.0001915545,0.5438034,0.00405329,0.001658438,0.0001821907,0.03260175,0.01026689,0.001467094,0.1103385,0.0009745836,0.2939341],"study_design_scores_gemma":[0.006111987,0.0008874427,0.4085517,0.01029724,0.000278814,0.004060081,0.01145162,0.09147029,0.001068595,0.06041788,0.4022094,0.003194944],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9662415,0.0127142,0.01468607,0.002953833,0.0005624864,0.0001007525,0.00002553589,0.00001745587,0.002698146],"genre_scores_gemma":[0.9957689,0.00225646,0.001353901,0.00005100031,0.0002463816,0.000002793611,0.000001622481,0.00002342995,0.0002955204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4012349,"threshold_uncertainty_score":0.5483806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02419828092240885,"score_gpt":0.2142297441160448,"score_spread":0.1900314631936359,"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."}}