{"id":"W4391840798","doi":"10.3390/s24041230","title":"Hyperparameter Optimization with Genetic Algorithms and XGBoost: A Step Forward in Smart Grid Fraud Detection","year":2024,"lang":"en","type":"article","venue":"Sensors","topic":"Electricity Theft Detection Techniques","field":"Engineering","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Hyperparameter; Hyperparameter optimization; Computer science; Machine learning; Genetic algorithm; Precision and recall; Artificial intelligence; Algorithm; Metaheuristic; Grid; Smart grid; Data mining; Support vector machine; Engineering; 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":[0.00007727688,0.0001379245,0.0001217268,0.0003454203,0.00002771543,0.00006472324,0.00003621168,0.00009845125,0.00001132744],"category_scores_gemma":[0.00001238086,0.0001296474,0.00002323124,0.0004632722,0.00002242269,0.00009534194,0.000008837181,0.0002130823,0.000009584295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009775648,"about_ca_system_score_gemma":0.000006493045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006513172,"about_ca_topic_score_gemma":0.000105466,"domain_scores_codex":[0.9993373,0.00002587198,0.0001467918,0.0001987806,0.0001074387,0.0001838308],"domain_scores_gemma":[0.999772,0.0000438821,0.00001111917,0.0001137209,0.00001937564,0.00003986607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003288134,0.00001469512,0.0005393393,0.0001956289,0.0000763866,0.00007343084,0.0004535656,0.7611321,0.006679602,0.000008210466,0.0001012941,0.2306929],"study_design_scores_gemma":[0.0001231516,0.0001458782,0.0006691981,0.00005330212,0.00001791037,0.0001178123,0.00002264681,0.9448553,0.05281224,0.00005303059,0.00095434,0.0001751673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7168745,0.0004817071,0.2808131,0.00002173569,0.0001947789,0.0002541392,0.000003328003,0.001014029,0.0003426493],"genre_scores_gemma":[0.9669162,0.0002573418,0.03255757,0.00001697715,0.00007074793,0.00004035721,0.000002130016,0.00005924623,0.00007943407],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2500417,"threshold_uncertainty_score":0.5286866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0041796830002364,"score_gpt":0.1896710604519166,"score_spread":0.1854913774516802,"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."}}