{"id":"W4399247232","doi":"10.58346/jisis.2024.i2.008","title":"OptCatB: Optuna Hyperparameter Optimization Model to Forecast the Educational Proficiency of Immigrant Students based on CatBoost Regression","year":2024,"lang":"en","type":"article","venue":"Journal of Internet Services and Information Security","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hyperparameter; Immigration; Socioeconomic status; Reading (process); Poverty; Computer science; Educational attainment; Psychology; Machine learning; Mathematics education; Geography; Demography; Sociology; Political science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005006832,0.0000923306,0.0001245358,0.0002419414,0.00004834402,0.0003676321,0.0005370278,0.00003697036,0.000007881499],"category_scores_gemma":[0.00002669181,0.00005284754,0.0000660021,0.0002502178,0.00001597767,0.00154692,0.0001007832,0.0001806457,0.000005185615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002920672,"about_ca_system_score_gemma":0.00009000429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003487424,"about_ca_topic_score_gemma":0.000003135514,"domain_scores_codex":[0.9988529,0.00003175598,0.0004811036,0.00008008241,0.000466299,0.00008787127],"domain_scores_gemma":[0.9990926,0.00007162213,0.0003076313,0.000141605,0.000322095,0.00006439212],"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":[0.00007188958,0.000200257,0.00095535,0.0003812128,0.00003684792,0.000001045716,0.02525361,0.9557369,0.00001661744,0.01022296,0.0006970477,0.006426225],"study_design_scores_gemma":[0.0001433342,0.0002205978,0.0006333714,0.000531591,0.00001057633,0.00001419951,0.0004215198,0.9970192,0.00009502121,0.0003374977,0.0005136944,0.00005941328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6769336,0.0001906789,0.3050489,0.01657741,0.0005231517,0.0002043972,0.00001515268,0.0000207549,0.0004858897],"genre_scores_gemma":[0.9901764,0.00003363776,0.008657409,0.001038878,0.00004395814,0.00000197194,0.000007513872,0.000002961262,0.00003724435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3132428,"threshold_uncertainty_score":0.3545085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008647900684736264,"score_gpt":0.2847658147457898,"score_spread":0.2761179140610535,"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."}}