Analysis Code for "Do Standardized Residential Energy Models Represent the Variables That Matter? Evidence from Explainable Machine Learning"

Abstract

Title: Analysis Code for “Do Standardized Residential Energy Models Represent the Variables That Matter? Evidence from Explainable Machine Learning” Creators: Jie Li, Guido Cervone, José P. Duarte, Ute Poerschke, and Lisa D. Iulo Description: This repository contains the analysis code supporting the study “Do Standardized Residential Energy Models Represent the Variables That Matter? Evidence from Explainable Machine Learning,” published in Energy and AI. The code implements the machine-learning and explainable-AI workflow used in the study, including XGBoost modelling and SHAP-based feature attribution applied to residential energy datasets to assess representation adequacy in standardized residential energy modelling. Keywords: XGBoostSHAPbuilding energyresidential energyexplainable machine learningrepresentation adequacyenergy simulation License: MIT Related identifier: 10.1016/j.egyai.2026.100904Relation: Is supplement toResource type: Publication / Journal article