Deep Reinforcement Learning and Evolutionary Strategies for High Frequency Trading

• Grant number: 23/00441-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2023
• End date: June 30, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: André Carlos Ponce de Leon Ferreira de Carvalho
• Grantee: Thiago Ambiel
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The objective of this work is to investigate two classes of reinforcement learning algorithms for the development of High-Frequency Trading strategies: Deep Reinforcement Learning algorithms and Reinforcement Learning algorithms through Evolutionary Optimizers. Initially, we propose the development of a realistic simulator of the Brazilian stock market, with the purpose of allowing the training and performance analysis of the algotrading algorithms. Subsequently, reinforcement learning algorithms from the above-mentioned two classes will be implemented, using Deep Neural Networks and Decision Trees as the structure for the models.