{"id":"W3105640742","doi":"10.28945/4184","title":"A New Typology Design of Performance Metrics to Measure Errors in Machine Learning Regression Algorithms","year":2019,"lang":"en","type":"article","venue":"Interdisciplinary Journal of Information Knowledge and Management","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":611,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Metric (unit); Machine learning; Measure (data warehouse); Data mining; Construct (python library); Mean squared error; Artificial intelligence; Algorithm; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002551316,0.0000965306,0.0002481348,0.001401841,0.000067858,0.00004406786,0.0004089872,0.0000455015,0.0000579517],"category_scores_gemma":[0.000139937,0.00006493655,0.00005503746,0.0009912529,0.00001906407,0.0006765133,0.0005778249,0.0001757598,0.00006668347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000523186,"about_ca_system_score_gemma":0.00003419135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002346997,"about_ca_topic_score_gemma":0.000003502944,"domain_scores_codex":[0.9983802,0.00007328598,0.0009448337,0.00009522656,0.0003875432,0.00011884],"domain_scores_gemma":[0.9986687,0.0001575722,0.0005957655,0.0001685199,0.0003284398,0.00008098452],"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":[0.0003403781,0.00006930029,0.00542009,0.00008364168,0.0000291751,0.000002857662,0.007586217,0.008745325,0.00006445318,0.00242297,0.01023085,0.9650047],"study_design_scores_gemma":[0.00580206,0.008425968,0.05741786,0.003928529,0.0001215115,0.0003990163,0.02326948,0.6234728,0.00305142,0.02699704,0.2461372,0.0009772414],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09868644,0.0003525212,0.8803867,0.001023776,0.0003494489,0.0005964841,0.00000199836,0.0000171418,0.01858548],"genre_scores_gemma":[0.9313822,0.0001415734,0.06745537,0.00002768131,0.00002004683,0.000005879094,0.00000145616,0.000004412474,0.0009613348],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9640275,"threshold_uncertainty_score":0.2648036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06740766856238833,"score_gpt":0.3730869472578724,"score_spread":0.3056792786954841,"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."}}