Summary
This document is a guide that outlines the methodology for predicting energy pricing using historical energy generation data. It describes the use of the Shapelets platform to build a data application aimed at improving price predictions in the energy market. The guide details the steps involved in the process, including data extraction from the Operador del Mercado Ibérico-Polo español (OMIE) API, which provides various indicators for analysis. It emphasizes the importance of understanding the relationship between energy pricing and generation data, particularly in the context of the Spanish energy market. The methodology includes exploratory data analysis, data processing, and the application of machine learning algorithms such as Random Forest, LightGBM, and XGBoost to develop predictive models. The guide also discusses the evaluation of model performance using regression error metrics, highlighting the significance of accurate energy price forecasting for informed decision-making in energy usage and investment. Overall, the document serves as a comprehensive resource for data scientists and analysts interested in energy price prediction.
