{"id":"W2737123405","doi":"10.5539/hes.v7n3p42","title":"Early Detection of At-Risk Undergraduate Students through Academic Performance Predictors","year":2017,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychological intervention; Medical education; Psychology; Academic achievement; At-risk students; Linear discriminant analysis; Sample (material); Academic institution; Dropout (neural networks); Higher education; Regression analysis; Mathematics education; Medicine; Statistics; Computer science; Political science; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001769418,0.0001091945,0.0001617406,0.00005218003,0.000672079,0.00006635785,0.0006967841,0.00004927101,0.000001817682],"category_scores_gemma":[0.00004310907,0.00009348609,0.00004349912,0.0001101351,0.0001195438,0.0005374773,0.0003775503,0.0001876288,0.00004502786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000073088,"about_ca_system_score_gemma":0.00004823532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007243855,"about_ca_topic_score_gemma":0.000004981008,"domain_scores_codex":[0.9990327,0.00004549688,0.0002199225,0.0002380234,0.0003177232,0.0001461367],"domain_scores_gemma":[0.998701,0.00004730115,0.0004626953,0.0005290455,0.0002276103,0.00003233338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004842688,0.00007322837,0.9912617,0.00003848101,0.000121507,1.406177e-7,0.001570285,0.00004286592,0.0001441707,0.001626025,0.000769433,0.004347366],"study_design_scores_gemma":[0.0001625785,0.00007864347,0.9898649,0.00006772469,0.00003735424,7.719354e-7,0.00010649,0.0001697889,0.000847032,0.002065313,0.006498362,0.0001009682],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9936913,0.001076078,0.0004369291,0.002280968,0.002037504,0.00006175465,0.000001095886,0.00006307068,0.0003513575],"genre_scores_gemma":[0.9871107,0.002044397,0.0008020216,0.00005061467,0.000217483,0.00001399455,7.564171e-7,0.000006915553,0.009753123],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009401766,"threshold_uncertainty_score":0.5169157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04225285332220821,"score_gpt":0.3773914158058378,"score_spread":0.3351385624836296,"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."}}