Open Access

ARTICLE

Month-Conditioned Boosting Framework with SHAP-in-the-Loop for Short-Term Electricity Load Forecasting

Jinsung Park^1,#, Jaehyuk Lee^1,2,#, Eunchan Kim^1,3,*

1 Department of Information Systems, Hanyang University, Seoul, Republic of Korea
2 Institute of IT Convergence Technology, Seoul National University of Science and Technology, Seoul, Republic of Korea
3 Department of Artificial Intelligence, Hanyang University, Seoul, Republic of Korea

* Corresponding Author: Eunchan Kim. Email:
# These authors contributed equally to this work

Computers, Materials & Continua 2026, 88(1), 50 https://doi.org/10.32604/cmc.2026.079734

Received 27 January 2026; Accepted 19 March 2026; Issue published 08 May 2026

Abstract

Accurate short-term load forecasting is essential for reliable power system operation, particularly under the increasing uncertainty caused by abnormal weather and socio-economic fluctuations. This study presents a month-conditioned boosting framework that integrates SHapley Additive Explanations (SHAPs) into model refinement. A baseline XGBoost model was first compared with linear and tree-based regressors, followed by enhancements through lagged and rolling-window features as well as loss weighting for vulnerable months. To further improve the performance, SHAP analysis was employed to identify the dominant error-contributing features, which guided the construction of targeted month-specific interaction terms for retraining. Experimental results based on rolling-origin cross-validation showed that this approach significantly reduced the RMSE and MAPE, particularly during high-variance summer months. Moreover, the SHAP interpretation revealed the varying roles of seasonal demand structures and socio-economic mobility, thereby enhancing transparency and operational insight. The proposed framework demonstrated that embedding explainability into the learning loop improved predictive accuracy and ensured interpretability, offering a data-driven solution for electricity demand forecasting in practical settings.

---

Keywords

---