<![CDATA[Efficient energy management has become a critical concern across all sectors due to rising costs and sustainability imperatives. In universities, electricity expenditure represents a substantial share of operational budgets, prompting the need for accurate forecasting models to support financial planning and sustainability initiatives. This study proposed a hybrid forecasting model integrating Simple Exponential Smoothing (SES) and Long Short-Term Memory (LSTM) networks to predict monthly electricity expenditure in a university setting. SES acts as a linear smoothing operator, emphasizing recent trends, while LSTM serves as a nonlinear sequence learner capable of modeling long-term dependencies. The hybrid formulation embeds SES forecasts as auxiliary input features to LSTM, thereby balancing interpretability with predictive power. A dataset of 60 monthly electricity expenditure observations (2019–2023) from Eastern Visayas State University–Tanauan Campus was analyzed. The proposed model was compared against classical (SES, ARIMA) and deep learning (LSTM, FB Prophet) approaches. Results show that the hybrid model achieved superior performance (RMSE = 33760.68, MAPE = 32.32%, MAE = 24580.12), with statistical validation through the Diebold-Mariano test, which confirmed significant improvements. Residual and uncertainty analyses demonstrated the model's robustness and practical applicability. The proposed model positioned it as a valuable decision-support tool for energy cost forecasting and risk-aware planning in universities.]]>
