{"id":"W4362698458","doi":"10.1038/s41598-023-32484-w","title":"Using machine learning to predict student retention from socio-demographic characteristics and app-based engagement metrics","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Predictive power; Dropout (neural networks); Generalizability theory; Mentorship; Computer science; Student engagement; Predictive analytics; Centrality; Predictive validity; Psychology; Macro; Learning analytics; Machine learning; Medical education; Mathematics education; Medicine; Statistics","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":[0.002829266,0.001006311,0.0007452751,0.003483431,0.0004592072,0.001590665,0.0008850869,0.0009204701,0.002073187],"category_scores_gemma":[0.01199751,0.000253959,0.0008734501,0.001819062,0.0003153079,0.001266814,0.001149745,0.001826106,0.001642271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004603019,"about_ca_system_score_gemma":0.0008096664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005750497,"about_ca_topic_score_gemma":0.008056941,"domain_scores_codex":[0.9989182,0.0003773647,0.0001033043,0.0002102018,0.000220611,0.0001702561],"domain_scores_gemma":[0.9918972,0.004541278,0.001276991,0.0005511848,0.001066512,0.0006667822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002481055,0.0009419954,0.8783191,0.00009462917,0.0001821121,0.000103086,0.0002542828,0.01648095,0.0006061845,0.0003089373,0.002904981,0.09955555],"study_design_scores_gemma":[0.00004412741,0.001169068,0.3443335,0.0002098898,0.0001513957,0.0001961857,0.00111431,0.6423711,0.001760824,0.004999034,0.003572785,0.00007783058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9579011,0.0004482415,0.03340448,0.0009915938,0.00008195447,0.0001989452,0.003665266,0.0008204045,0.00248794],"genre_scores_gemma":[0.9863232,0.0001715321,0.008729142,0.0001102035,0.00006750635,0.0001623346,0.003384174,0.00002499961,0.001026889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005750497,"threshold_uncertainty_score":0.01496279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0421789404460062,"score_gpt":0.3052658242393649,"score_spread":0.2630868837933587,"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."}}