{"id":"W4403873331","doi":"10.1007/s10639-024-13110-2","title":"Stacking: An ensemble learning approach to predict student performance in PISA 2022","year":2024,"lang":"en","type":"article","venue":"Education and Information Technologies","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Educational technology; Stacking; Mathematics education; Computer science; Ensemble learning; Academic achievement; Psychology; Artificial intelligence; Machine learning; Chemistry","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001298467,0.001167308,0.0009510367,0.002012972,0.0006162288,0.0009899989,0.0007585479,0.0009221653,0.002962946],"category_scores_gemma":[0.002833683,0.0002651572,0.0009092816,0.001699343,0.0001479456,0.0009154092,0.001139722,0.001441121,0.002599092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004142369,"about_ca_system_score_gemma":0.0007978004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009389702,"about_ca_topic_score_gemma":0.01303316,"domain_scores_codex":[0.9994032,0.0001500372,0.0000354581,0.000151153,0.0001357947,0.0001242948],"domain_scores_gemma":[0.9986402,0.0004944438,0.00008995816,0.000184189,0.0004203533,0.0001708241],"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":[0.001022073,0.001274985,0.1907094,0.00009957951,0.0007966034,0.0003097537,0.0002368565,0.2242585,0.002490032,0.0009245825,0.05141514,0.5264626],"study_design_scores_gemma":[0.00002129039,0.0003289258,0.04966062,0.00001754228,0.0001107662,0.00004658615,0.000174703,0.9427992,0.001963354,0.001787562,0.003044815,0.00004467211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8743208,0.00092609,0.09300179,0.001387165,0.000770817,0.000134549,0.01507542,0.006152013,0.00823131],"genre_scores_gemma":[0.9534109,0.0002208319,0.02259592,0.0001006162,0.0002104359,0.0001187266,0.01588089,0.0001279298,0.007333697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009389702,"threshold_uncertainty_score":0.01867008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009919942040356072,"score_gpt":0.278071289975247,"score_spread":0.2681513479348909,"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."}}