{"id":"W3183491169","doi":"10.1145/3468784.3470656","title":"Building Energy Consumption Forecasting: A Comparison of Gradient Boosting Models","year":2021,"lang":"en","type":"article","venue":"","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Gradient boosting; Computer science; Boosting (machine learning); Machine learning; Energy consumption; Artificial intelligence; Building management system; Efficient energy use; Sustainability; Context (archaeology); Work (physics); Random forest; Engineering","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":[0.004308328,0.0009704923,0.001341896,0.001196627,0.0003843663,0.00103206,0.001578542,0.001162929,0.0010658],"category_scores_gemma":[0.004628132,0.0003262771,0.0009139302,0.001270262,0.0002958101,0.001012479,0.00057778,0.001213938,0.0005210983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009733518,"about_ca_system_score_gemma":0.001141306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0132667,"about_ca_topic_score_gemma":0.009316431,"domain_scores_codex":[0.9990074,0.0004513013,0.00005307742,0.0001425964,0.0002560182,0.00008951644],"domain_scores_gemma":[0.9978499,0.001190807,0.0001078919,0.000176323,0.0005735026,0.0001016204],"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":[0.0005256539,0.000285614,0.006350145,0.0001243446,0.0001753688,0.00003170561,0.00003461321,0.885219,0.0005038645,0.00183299,0.004140197,0.1007764],"study_design_scores_gemma":[0.00001126095,0.00004578901,0.000884197,0.0000111466,0.00001117617,0.000004877072,0.000007373843,0.9978539,0.0002735863,0.0004558572,0.000436228,0.000004595392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.567515,0.008780693,0.3914495,0.003145577,0.001255028,0.0004084998,0.001466546,0.003460363,0.02251888],"genre_scores_gemma":[0.934354,0.001027125,0.06106233,0.0002901149,0.0001367082,0.00009958521,0.0011341,0.0001066426,0.001789406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0132667,"threshold_uncertainty_score":0.02637899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05679535891102353,"score_gpt":0.2500825588592854,"score_spread":0.1932871999482619,"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."}}