{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002022339,0.0002054051,0.0002370464,0.00009567495,0.0003589314,0.0002753486,0.0007855791,0.00004541466,0.0000134662],"category_scores_gemma":[0.0009736035,0.0001905029,0.00003319782,0.0004320681,0.00002063014,0.001680084,0.0005567123,0.0004593974,0.00002853004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003988345,"about_ca_system_score_gemma":0.00003585907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572107,"about_ca_topic_score_gemma":6.304853e-7,"domain_scores_codex":[0.9976035,0.0008404233,0.000309073,0.0005851585,0.0003968904,0.000264973],"domain_scores_gemma":[0.9989898,0.0002381279,0.0001759291,0.0004236317,0.00006096451,0.0001115301],"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":[0.00003345795,0.00008482142,0.01283607,0.00001784265,0.00001384492,0.000009724229,0.01068433,0.2386116,0.0005024699,0.0001394863,0.00003356554,0.7370328],"study_design_scores_gemma":[0.0001929182,0.002742896,0.00179676,0.00003048672,0.0000104596,0.00001237748,0.0000859712,0.9939082,0.000591326,0.0003786011,0.00004915857,0.0002008493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3462314,0.000007882085,0.6515204,0.0004135149,0.00002401126,0.0001759307,0.00000100388,0.0009903993,0.0006354444],"genre_scores_gemma":[0.4618991,3.203216e-7,0.5378457,0.000148994,0.00003325177,0.00001757212,0.00001417836,0.00001573779,0.00002516716],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7552966,"threshold_uncertainty_score":0.7768481,"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."}}