A Trustworthy By Design Classification Model for Building Energy Retrofit Decision Support

TL;DR

The paper tackles retrofit decision support for residential buildings under data scarcity and regulatory scrutiny by proposing a trustworthy-by-design framework that combines a multi-label neural classifier with SHAP explanations and CTGAN-based data augmentation. It demonstrates the approach on two diverse case studies—the UK England and Wales EPC dataset and Latvia's RETROFIT-LAT—showing improved predictive performance and interpretability while highlighting regulatory alignment and usability for non-technical stakeholders. Key contributions include direct multi-measure retrofit recommendations, an explainability-driven feature engineering process, and a GAN-based augmentation layer that mitigates class imbalance. The work advances practical, transparent, and scalable AI-enabled retrofit planning that can inform policy, investment decisions, and transfer to different regional building stocks.

Abstract

Improving energy efficiency in residential buildings is critical to combating climate change and reducing greenhouse gas emissions. Retrofitting existing buildings, which contribute a significant share of energy use, is therefore a key priority, especially in regions with outdated building stock. Artificial Intelligence (AI) and Machine Learning (ML) can automate retrofit decision-making and find retrofit strategies. However, their use faces challenges of data availability, model transparency, and compliance with national and EU AI regulations including the AI act, ethics guidelines and the ALTAI. This paper presents a trustworthy-by-design ML-based decision support framework that recommends energy efficiency strategies for residential buildings using minimal user-accessible inputs. The framework merges Conditional Tabular Generative Adversarial Networks (CTGAN) to augment limited and imbalanced data with a neural network-based multi-label classifier that predicts potential combinations of retrofit actions. To support explanation and trustworthiness, an Explainable AI (XAI) layer using SHapley Additive exPlanations (SHAP) clarifies the rationale behind recommendations and guides feature engineering. Two case studies validate performance and generalization: the first leveraging a well-established, large EPC dataset for England and Wales; the second using a small, imbalanced post-retrofit dataset from Latvia (RETROFIT-LAT). Results show that the framework can handle diverse data conditions and improve performance up to 53% compared to the baseline. Overall, the proposed framework provides a feasible, interpretable, and trustworthy AI system for building retrofit decision support through assured performance, usability, and transparency to aid stakeholders in prioritizing effective energy investments and support regulation-compliant, data-driven innovation in sustainable energy transition.

Figures (15)

• Figure 1: Overview of the proposed framework regarding both its design and deployment phase
• Figure 2: Energy efficiency measures (target columns) distributions in initial UK data
• Figure 3: Summary plots of SHAP values for each retrofit class in the UK dataset with the final feature set
• Figure 4: Energy efficiency measures (target columns) distributions in synthetic UK data
• Figure 5: Column Shape Score per column of the UK dataset