Enhanced Electric Load Forecasting with Weather and Economic indicators using Machine Learning Models

Electric load forecasting is crucial for efficient energy management.This paper proposes a robust time-series forecasting system that predicts the daily electricity demand using additional features such as the 10-year break-even inflation, weather, unemployment rate and holidays. Among the machine learning models evaluated, CatBoost demonstrated the best performance due to its ability to effectively capture both general trends and seasonal patterns. This work highlights the idea of incorporating economic indicators to improve electricity demand forecasting.