{"id":"W2963558246","doi":"10.1109/access.2019.2930069","title":"An End-to-End Adaptive Input Selection With Dynamic Weights for Forecasting Multivariate Time Series","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"National Research Foundation of Korea; National IT Industry Promotion Agency; National Research Foundation","keywords":"Computer science; Benchmark (surveying); Multivariate statistics; Context (archaeology); Artificial intelligence; Recurrent neural network; Time series; Artificial neural network; Machine learning; Selection (genetic algorithm); Series (stratigraphy); Variable (mathematics); End-to-end principle; Feature selection; Data mining","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":[0.0008295959,0.001191834,0.000666105,0.0003972353,0.0003477475,0.000528247,0.001411073,0.0008111101,0.002138545],"category_scores_gemma":[0.001907774,0.0003599593,0.0004350632,0.000574018,0.0002704186,0.00111042,0.0007375094,0.001410962,0.0009535186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003750834,"about_ca_system_score_gemma":0.0006801552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004254574,"about_ca_topic_score_gemma":0.007593757,"domain_scores_codex":[0.9997076,0.00005103552,0.00002201081,0.00009859924,0.00007464804,0.00004606658],"domain_scores_gemma":[0.9995585,0.0001442455,0.00003892661,0.00007302945,0.0001576586,0.00002757237],"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":[0.0005002435,0.0004039063,0.003249742,0.00009851685,0.0001196779,0.0002615414,0.0001117542,0.3104696,0.0260803,0.002753613,0.005807042,0.6501441],"study_design_scores_gemma":[0.000006425309,0.00004417345,0.0003195547,0.000004045414,0.00001008054,0.00001889708,0.000007380217,0.9921879,0.005877688,0.001125037,0.0003922644,0.00000664033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05252682,0.0003439386,0.9414214,0.0001645788,0.0001029482,0.00008734417,0.0002177269,0.003463604,0.001671643],"genre_scores_gemma":[0.7418432,0.000257789,0.2517976,0.0001921906,0.00008166098,0.0001589452,0.0008254942,0.0001309018,0.004712169],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004254574,"threshold_uncertainty_score":0.008459628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09419881479961732,"score_gpt":0.4004594227550289,"score_spread":0.3062606079554115,"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."}}