{"id":"W4236370022","doi":"10.26868/25222708.2019.211250","title":"Building Energy Use Surrogate Model Feature Selection – A Methodology Using Forward Stepwise Selection and LASSO Regression Methods","year":2020,"lang":"en","type":"article","venue":"Building Simulation Conference proceedings","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Ontario Centres of Excellence","keywords":"Lasso (programming language); Feature selection; Stepwise regression; Selection (genetic algorithm); Computer science; Artificial intelligence; Regression; Elastic net regularization; Machine learning; Regression analysis; Energy (signal processing); Surrogate model; Feature (linguistics); Pattern recognition (psychology); Statistics; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005469564,0.0004061743,0.0004475784,0.0002749838,0.0003149837,0.0003291979,0.0001355646,0.0003721732,0.000009600027],"category_scores_gemma":[0.0006622786,0.0004160223,0.00008332595,0.0007258571,0.00003563213,0.00122288,0.00008963337,0.0004356565,3.851696e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001447956,"about_ca_system_score_gemma":0.00004851673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004327778,"about_ca_topic_score_gemma":0.000009074466,"domain_scores_codex":[0.9982276,0.00008765417,0.0003999619,0.0005782041,0.0002334768,0.0004730856],"domain_scores_gemma":[0.9987307,0.0003689577,0.0002088963,0.000062976,0.0003988628,0.000229597],"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":[0.00004754432,0.000004295585,0.0009519612,0.00009391105,0.00003587921,4.371643e-7,0.000697047,0.6653428,0.3152215,0.006419522,0.00005790908,0.01112719],"study_design_scores_gemma":[0.0003746008,0.0000541949,0.00006393015,0.0001700494,0.00007694757,0.0000197496,0.00005322162,0.9310551,0.06365022,0.002046721,0.002035206,0.0004000574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.391477,0.00007901884,0.6075965,0.0001024449,0.000113135,0.00009285679,0.000002734354,0.0004808029,0.00005546432],"genre_scores_gemma":[0.5814468,0.00003154002,0.4182096,0.00008615614,0.0001408455,0.00000861464,0.000003575477,0.00005187108,0.00002098724],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2657123,"threshold_uncertainty_score":0.9998292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1171066999554717,"score_gpt":0.3499509413432064,"score_spread":0.2328442413877346,"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."}}