AI in Finance: Transformers applied to multivariate time series forecasting

In this project, the exploration and evaluation of transformers as alternatives to long short-term memory (LSTM) technology in multivariate time series analysis in the financial sector isconducted. In summary, this project seeks to develop a thorough comparison between current AI systems fortime series prediction, adding an innovative system that can accurately predict market prices,using transformers and multivariate analysis. The comparison with LSTM technology and thefocus on market sentiment and stock volume as key variables for price prediction make thisproject a significant contribution to the field of Artificial Intelligence applied to finance.