The Use of The SHAP Algorithm in Building Energy Efficiency: A Bibliometric Analysis
Öz
Buildings account for a significant percentage of global energy consumption. Optimizing building energy consumption is important in terms of reducing carbon emissions and environmental impacts. In particular, with the advancement of technology in recent years, the use of artificial intelligence algorithms has gained importance in the field of building energy efficiency. Machine learning algorithms are used as an effective method for optimizing building energy consumption and predicting models, but these algorithms have limited interpretability. In studies conducted in the literature, the SHAP algorithm stands out as a powerful analysis algorithm that explains these unexplained prediction models, makes them easier to interpret, and explains the effects of variables. This study aims to examine the use of the Shapley Additive Explanations (SHAP) algorithm, one of the interpretable machine learning approaches, in energy efficiency prediction and evaluation using a bibliometric and systematic approach. In this context, 162 studies published between 2016 and 2025 were identified using the Scopus database in the first stage. Subsequently, bibliometric analysis was performed on 70 studies published between 2020 and 2025, applying inclusion-exclusion criteria appropriate to the study's objectives. The bibliometric analysis was conducted using the VOSviewer software tool. This analysis evaluated the trends of the SHAP algorithm in the field of building energy efficiency according to countries, institutions, journals, author collaborations, publication years, and keyword relationships. The results of the study show that SHAP is becoming increasingly popular in the field of building energy efficiency and is being used in conjunction with different machine learning algorithms. This study aims to guide future research by revealing the current status and trends of the SHAP algorithm in the field of building energy efficiency.
Anahtar Kelimeler
AI algorithms, building energy efficiency, explainable AI, machine learning algorithms, SHAP algorithm
Kaynakça
- Abdelaziz, A., Santos, V., & Dias, M. S. (2021). Machine learning techniques in the energy consumption of buildings: A systematic literature review using text mining and bibliometric analysis. Energies, 14(22). https://doi.org/10.3390/en14227810
- Alsamraee, S. A., & Khanna, S. (2025). High-resolution energy consumption forecasting of a university campus power plant based on advanced machine learning techniques. Energy Strategy Reviews, 60. https://doi.org/10.1016/j.esr.2025.101769
- Chen, C., Gao, Z., Zhou, X., Wang, M., & Yan, J. (2025). Dynamic energy consumption quota for public buildings based on multi-level classification and data correction. Journal of Building Engineering, 99. https://doi.org/10.1016/j.jobe.2024.111618
- Chen, Z., Xiao, F., Guo, F., & Yan, J. (2023). Interpretable machine learning for building energy management: A state-of-the-art review. Advances in Applied Energy, 9. https://doi.org/10.1016/j.adapen.2023.100123
- Cui, X., Lee, M., Koo, C., & Hong, T. (2024). Energy consumption prediction and household feature analysis for different residential building types using machine learning and SHAP: Toward energy-efficient buildings. Energy and Buildings, 309. https://doi.org/10.1016/j.enbuild.2024.113997
- Geng, S., Wang, Y., Zuo, J., Zhou, Z., Du, H., & Mao, G. (2017). Building life cycle assessment research: A review by bibliometric analysis. Renewable and Sustainable Energy Reviews, 76, 176-184. https://doi.org/10.1016/j.rser.2017.03.068
- Hatami, A. M., Sabour, M. R., Hajbabaie, M. R., & Nematollahi, H. (2022). Global trends of VOSviewer research, emphasizing Environment and Energy areas: A bibliometric analysis during 2000-2020. Environmental Energy and Economic Research, 6(1), 1-11. https://doi.org/10.22097/EEER.2021.301784.1216
- Kangalli Uyar, S. G., Ozbay, B. K., & Dal, B. (2025). Interpretable building energy performance prediction using XGBoost Quantile Regression. Energy and Buildings, 340. https://doi.org/10.1016/j.enbuild.2025.115815
- Kemeç, A., & Altınay, A. T. (2023). Sustainable Energy Research Trend: A Bibliometric Analysis Using VOSviewer, RStudio Bibliometrix, and CiteSpace Software Tools. Sustainability (Switzerland), 15(4). https://doi.org/10.3390/su15043618
- Korsavi, S. S., Azari, R., Iulo, L. D., & Mahdavi, M. (2025). Determinants of U.S. residential energy consumption at national and state levels: Policy implications. Energy Policy, 202. https://doi.org/10.1016/j.enpol.2025.114594