Multi-source data ensemble for energy price trend forecasting

Price trend prediction is critical across sectors, including finance, energy, and supply chains, guiding strategic decision -making. Machine Learning's rise, fueled by abundant data and computational power, has transformed trend prediction. Advanced algorithms enable precise forecasting. The Brazilian Energy Commercialization Platform shapes the nation's energy sector, influencing electricity contract trading. Despite opportunities, the Brazilian energy market faces liquidity challenges. This research introduces ensemble strategies utilizing diverse data sources and machine learning to enhance price trend prediction accuracy. One of the main contributions of this study is to investigate how the use of different data sources can improve the prediction of energy prices. The study considers Close -to -Close, Intraday, and Day Ahead trends, incorporating technical indicators, water flow rates, energy storage, precipitation, and load data. Employing stacking and performance -weighted averages, the proposed strategies aim to synergistically improve prediction accuracy and financial returns in the Brazilian energy market.