“Enhancing Electricity Price Forecasting”: Integrating Macro-Economic Factors and Renewable Energy Dynamics in A Machine Learning Approach

In the ever-evolving electricity market, accurate price prediction is imperative for informed decision-making. This research introduces an innovative predictive model that integrates renewable energy, macro-economic indicators, and external factors to enhance forecasting accuracy. By exploring historical trends, comparing machine learning algorithms, and employing advanced feature selection methods, the study addresses the complexities of the electricity market, emphasizing economic indicators, geopolitical events, and demand-supply dynamics. Informed by a literature review, the research underscores the necessity of dynamic models in electricity price forecasting. Utilizing machine learning models such as linear regression, random forest, SVM, AdaBoost, and ARIMA, the study aims to improve prediction accuracy. With a robust methodology and comprehensive evaluation metrics (MAE, RMSE, MAPE), the research contributes valuable insights into electricity market dynamics, providing a variable dictionary for clarity and emphasizing the strategic implications of the superior random forest model for stakeholders in the electricity sector.