Energy Performance of Building Refurbishments: Predictive and Prescriptive AI-based Machine Learning Approaches

Abstract

The energy performance (EP) of buildings is critical for European governments to meet their decarbonization targets by 2050. In the context of European Union (EU) policies, which subsidize citizen-led building renovations, it is imperative to ascertain the efficacy of these renovations in significantly enhancing EP. This study relies on six AI-based machine learning (ML) algorithms to identify key predictors and prescribe measures for enhancing post-renovation EP in building refurbishments. The gradient boosting model outperforms the other ML models with an accuracy rate of 84.34 % as the most effective predictive model. Moreover, an analysis of numerous predictors in the experiment showed that implementing modern energy-efficient heating systems, optimizing dwelling characteristics, regular maintenance, investing in high-performance insulation materials, and understanding the dynamics of the occupants were relevant prescriptions for efficient energy-saving strategies. The results should enable market actors to make optimal decisions regarding EP refurbishments.