{"id":"W4411162674","doi":"10.1177/17442591251333144","title":"Comparative analysis of deep learning and tree-based models in power demand prediction: Accuracy, interpretability, and computational efficiency","year":2025,"lang":"en","type":"article","venue":"Journal of Building Physics","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Computer science; Boosting (machine learning); Gradient boosting; Random forest; Machine learning; Artificial intelligence; Predictive modelling; Extreme learning machine; Tree (set theory); Mean squared error; Data mining; Artificial neural network; Deep learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002059403,0.00009055023,0.0003430937,0.0002909181,0.00003708567,0.00002559075,0.00005494998,0.00003269922,0.000002132441],"category_scores_gemma":[0.00003181949,0.00008633372,0.00007331358,0.0005633252,0.00005039798,0.0001876593,0.00002255967,0.0002087495,1.398395e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000370889,"about_ca_system_score_gemma":0.00002074045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003199545,"about_ca_topic_score_gemma":0.000007189928,"domain_scores_codex":[0.9992946,0.00004152023,0.0003731871,0.00008126144,0.0001224488,0.00008693806],"domain_scores_gemma":[0.9992492,0.0004542814,0.0001345776,0.00003848561,0.0000918514,0.00003166092],"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":[0.00001993268,0.00002945609,0.03459741,0.00003886015,0.0002335385,9.465406e-7,0.001176873,0.9594813,0.00066403,0.0008443746,0.000001531671,0.002911773],"study_design_scores_gemma":[0.0003558616,0.00005184211,0.01412716,0.0001776561,0.0001635652,0.000001494257,0.0001276236,0.9821433,0.0007705479,0.002016072,0.000007385284,0.00005751442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5977216,0.0005440469,0.4012764,0.000006670525,0.00004709059,0.00001809963,0.000001989409,0.000006837473,0.0003772722],"genre_scores_gemma":[0.9968566,0.00002529036,0.003090638,0.000006341663,0.00001390102,5.766561e-7,0.000001808889,0.000003923761,9.535933e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.399135,"threshold_uncertainty_score":0.3520587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01100770810595475,"score_gpt":0.2656465409185356,"score_spread":0.2546388328125808,"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."}}