Publications

Research Article

Artificial intelligence methods applied to financial assets price forecasting in trading contexts with low (intraday) and very low (high-frequency) time frames

Abstract

Financial price fast forecasting for high-frequency algorithmic trading can be improved profitably by using simplified artificial intelligence models. There are several different methodologies for working in algorithmic trading, each specific to the context. The method proposed here is designed to prioritize better performance. The methodology uses a combination of different artificial intelligence techniques, some of which have been revised and simplified to maximize performance. The forecasting part is assigned to a formula based on the Petrelli-Cesarini (2018) index, specifically designed to speed up the calculation, allowing its use in operating environments with low time frames and high-frequency trading.