Deep Reinforcement Learning Applied to Investment Portfólio Management

• Grant number: 25/09148-8
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Start date: November 01, 2025
• End date: October 31, 2027
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Roberto Fix Ventura
• Grantee: Roberto Fix Ventura
• Associated research grant: 23/13484-8 - Deep Reinforcement Learning Applied to Investment Portfólio Management, AP.PIPE

Abstract

This project aims to develop and enhance Deep Reinforcement Learning (DRL) models applied to the automated management of investment portfolios. The proposal includes the creation of robust technological infrastructure for parallel training and optimization of DRL models, aiming to maximize risk-adjusted returns in real environments. The innovation includes integration with brokerage platforms for automated trading, an interactive front-end for investors, and a secure back-end for portfolio management. The acquisition of high-performance servers will enable scalability, massive processing of financial data, and simultaneous execution of complex strategies, ensuring greater precision in investment decisions. The expected technological maturity encompasses implementation in a real environment, with a pilot operation using real capital and investor feedback, positioning Tekton as a pioneer in AI solutions for quantitative investments. (AU)