Cross-Regional Methodological Validation of Ensemble and Kernel-Based Machine Learning Models for Automated Building Energy Performance Assessment
Abstract
This paper presents an extended machine learning framework for predicting building Energy Performance Certificate (EPC) scores and evaluates its consistency across regulatory and geographic contexts. Building on two prior single-context studies, the present work integrates four regression paradigms — SVR, Random Forest, XGBoost, and, AdaBoost — trained on the Seattle Building Energy Benchmarking dataset (34,709 records, 46 parameters) and evaluated against real municipal EPC and building-registry data collected from three Turkish administrative districts: Torbalı, Beşiktaş, and Ümraniye. A structured preprocessing pipeline addressing missing data, outlier treatment, correlation-driven feature reduction, and categorical encoding was applied consistently across all data sources. Among the four models, the tree-based ensembles outperformed both the kernel-based SVR and the boosting-based AdaBoost on both datasets, with XGBoost achieving the strongest fit on the Seattle benchmark (R² = 0.801) and again the strongest fit on the Torbalı municipal sample (R² = 0.824). Exploratory analysis of the Turkish municipal data further identifies insulation status, construction era, and heating-fuel type as the dominant levers for emissions reduction, with uninsulated buildings consuming approximately 71% more site energy than fully insulated stock. Unlike earlier single-dataset studies, this work removes optical character recognition (OCR) document ingestion from the scope and instead concentrates on a rigorous, side-by-side comparison of four learning paradigms across independent regional datasets, offering evidence for the predictive ceiling of ensemble learning on tabular energy data and for the conditions under which a smaller, locally collected dataset can achieve results comparable to those from a larger but less homogeneous metropolitan dataset.
Keywords
References
- [1] European Commission, "Energy Performance of Buildings Directive," Directorate-General for Energy, European Commission. [Online]. Available: https://energy.ec.europa.eu/topics/energy-efficiency/energy-performance-buildings/energy-performance-buildings-directive_en.
- [2] United Nations, "The 17 Goals | Sustainable Development," United Nations Department of Economic and Social Affairs, [Online]. Available: https://sdgs.un.org/goals.
- [3] D. G. Yılmaz and F. Cesur, "A Study for the Improvement of the Energy Performance Certificate (EPC) System in Turkey," Sustainability, vol. 15, no. 19, Art. no. 14074, Sep. 2023, doi: 10.3390/su151914074.
- [4] Bankacılık Düzenleme ve Denetleme Kurumu (BDDK), "Bankacılık Düzenleme ve Denetleme Kurulu Kararı, Karar Sayısı: 11165, 13 Mart 2025" [Banking Regulation and Supervision Board Decision No. 11165, Mar. 13, 2025], 2025. [Online]. Available: https://www.bddk.gov.tr/Mevzuat/DokumanGetir/1285.
- [5] U. Kınay and A. Laukkarinen, "Renovation wave of the residential building stock targets for the carbon-neutral: Evaluation by Finland and Türkiye case studies for energy demand," Buildings and Cities, 2023.
- [6] European Parliament and Council of the European Union, Directive 2002/91/EC of the European Parliament and of the Council of 16 December 2002 on the Energy Performance of Buildings, Official Journal of the European Communities, L 1, pp. 65–71, Jan. 4, 2003.
- [7] U.S. Environmental Protection Agency, ENERGY STAR Score: Technical Reference, ENERGY STAR Portfolio Manager, Apr. 2021. [Online]. Available: https://portfoliomanager.energystar.gov/pdf/reference/ENERGY%20STAR%20Score.pdf.
- [8] J. Scott, "Grid Edge: Artificial Intelligence for Energy Systems," presented at IEA Workshop on Modernising Energy Efficiency through Digitalisation, Paris, France, 2019.
Details
Primary Language
English
Subjects
Information Systems (Other), Reinforcement Learning, Semi- and Unsupervised Learning, Artificial Intelligence (Other)
Journal Section
Research Article
Early Pub Date
August 13, 2026
Publication Date
-
Submission Date
July 29, 2026
Acceptance Date
August 10, 2026
Published in Issue
Year 2026 Number: Advanced Online Publication