Forecasting Electricity Price Index with Machine Learning Models and Strategies

Electricity consumption is recognized as one of the fundamental indicators of economic activities. Accurate forecasting of electricity prices is therefore critical for economic planning and sustainable development. This research investigates the effectiveness of 19 different machine learning algorithms/models in forecasting the US electricity prices. It provides a comprehensive analysis by evaluating approaches that both include and exclude seasonality factors. Key findings of the study are as follows: (I) Linear Regression and CatBoost Regressor models delivered the best results in terms of accuracy and computational efficiency. (ii) The Linear Regression model using the TimeSeriesSplit strategy exhibited a high agreement with actual electricity price trends. (iii) Linear regression outperformed other models in metrics such as mean absolute error (MAE) and root mean squared logistic error (RMSLE). This study demonstrates that machine learning models can serve as effective tools for forecasting electricity prices and provide valuable recommendations for stakeholders in the energy sector. Especially when appropriate strategies for temporal data structures are applied, these models can offer reliable predictions. Eventually, this paper highlights that machine learning models are an important tool for stakeholders and policymakers in the energy sector, helping to predict electricity price fluctuations and contributing to the decision-making process.