{"id":"W2947014533","doi":"10.1007/s10994-020-05910-7","title":"Evaluating time series forecasting models: an empirical study on performance estimation methods","year":2020,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":386,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Fundação para a Ciência e a Tecnologia; Canada Research Chairs","keywords":"Series (stratigraphy); Computer science; Time series; Independent and identically distributed random variables; Dependency (UML); Machine learning; Data mining; Pipeline (software); Sample (material); Estimation; Artificial intelligence; Statistics; Mathematics; Random variable; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.06269631,0.001619071,0.001540588,0.003461691,0.000533007,0.003145619,0.001688063,0.002234378,0.0009880771],"category_scores_gemma":[0.238976,0.0004193472,0.001115725,0.003751607,0.001194526,0.006911852,0.001211724,0.001973297,0.0002180698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002121568,"about_ca_system_score_gemma":0.001482831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003298999,"about_ca_topic_score_gemma":0.00172362,"domain_scores_codex":[0.973111,0.01983759,0.001191589,0.001573063,0.0038126,0.0004741537],"domain_scores_gemma":[0.5285546,0.4442889,0.007990859,0.009076698,0.009070683,0.001018248],"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":[0.001514358,0.0008903836,0.1175065,0.0006239092,0.00105957,0.0001369357,0.0008070355,0.5465503,0.001722551,0.03194461,0.003467767,0.2937761],"study_design_scores_gemma":[0.0000359586,0.0005372001,0.01137591,0.0001146245,0.0001963167,0.00006030438,0.00022841,0.9749883,0.001520966,0.01019481,0.0007156186,0.00003157351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6567836,0.00877769,0.3253814,0.001695097,0.0001912203,0.0001956273,0.0004066571,0.0005503955,0.00601834],"genre_scores_gemma":[0.9596854,0.001360566,0.03768284,0.00009638788,0.0001042428,0.00006392613,0.0004386982,0.000104745,0.000463198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06269631,"threshold_uncertainty_score":0.3315737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2227258883317751,"score_gpt":0.4461106063891386,"score_spread":0.2233847180573635,"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."}}