Education institutions:

Technological Institute of Aeronautics

Pos-doctorate in Operations Research

I work at the intersection of AI and optimization, developing metaheuristics powered by function approximation techniques to solve high-dimensional combinatorial problems in operations research. My current focus is on Stochastic Lot Sizing and Facility Location problems, with an emphasis on modeling perishability and demand uncertainty. I integrate Graph Neural Networks (GNNs), Genetic Algorithms, Reinforcement Learning, and Dynamic Programming to approximate decision policies. The goal is to enhance supply chain efficiency, reduce food waste, and build scalable, adaptive optimization strategies for real-world impact.

Polytechnic of Turin - Department of Mathematical Sciences

Ph.D. in Applied Mathematics
Part of the double degree agreement between Universidade de São Paulo and Politecnico di Torino / L'Università di Torino. Researcher in the area of dynamic programming/approximated dynamic programming/reinforcement learning applied to the lot sizing problem.

Polytechnic School - University of Sao Paulo

Ph.D. in Computer Engineering

Grade: A

Atividades e grupos: .

-Member of ICONE research group.

-Teaching Assistant of the discipline PSI3472 - Design and Implementation of Intelligent Electronic System

Disciplines:

PCS5024-1/4 Aprendizado Estatístico - A

PCS5012-8/1 Metodologia de Pesquisa Científica em Engenharia de Computação - B

PCS5031-1/4 Introdução à Ciência dos Dados - A

PSI5886-4/1 Princípios de Neurocomputação - A

PCS5708-6/1 Técnicas de Raciocínio Probabilístico em Inteligência Artificial - A

Atividades e grupos: . -Member of ICONE research group. -Teaching Assistant of the discipline PSI3472 - Design and Implementation of Intelligent Electronic System Disciplines: PCS5024-1/4 Aprendizado Estatístico - A PCS5012-8/1 Metodologia de Pesquisa Científica em Engenharia de Computação - B PCS5031-1/4 Introdução à Ciência dos Dados - A PSI5886-4/1 Princípios de Neurocomputação - A PCS5708-6/1 Técnicas de Raciocínio Probabilístico em Inteligência Artificial - A

Doctoral Student at Programa de Pós-Graduação em Engenharia Elétrica (PPGEE) program. Research theme: Reinforcement Learning, Neural Networks, Time-Series, Deep Reinforcement Learning, Trading Systems and Trading Signals, Quantitative trading, Portfolio Management, Time-series Forecasting, Operational Research.Doctoral Student at Programa de Pós-Graduação em Engenharia Elétrica (PPGEE) program. Research theme: Reinforcement Learning, Neural Networks, Time-Series, Deep Reinforcement Learning, Trading Systems and Trading Signals, Quantitative trading, Portfolio Management, Time-series Forecasting, Operational Research.

Fundação Getulio Vargas

M.Sc.\ in Economics

Grade: 7.5/10

Atividades e grupos: 

Mathematics - 8.28/10

Microeconomics - 8.32/10

International finance - 8.43/10

Numerical methods in finance - 9.31/10

Statistics - 6.2/10

Master's thesis: A study on neural network architecture applied to predict the return of Brazilian stocks. Thesis presented at the National Association of Postgraduate and Research in Administration 2017 (Associação Nacional de Pós-Graduação e Pesquisa em Administração – EnANPAD) Congress.

Polytechnic School - University of Sao Paulo

Bachelor

Grade: 6.1/10

Atividades e grupos: 

Scientific initiation: FINEP Scholarship - Gestão do Processo do Projeto em Habitação de Interesse Social com o uso da Modelagem da Informação da Construção

Work published in the SIICUSP - 2014

Undergraduate course assistance: Road projects technical assistent

 Published academic works:

1. L. K. Felizardo, E. Fadda, P. Brandimarte, E. Del-Moral-Hernandez, M. C. V. Nascimento, "A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networks", arXiv preprint, arXiv:2504.05150, 2025. https://arxiv.org/abs/2504.05150 

2. Felizardo, L. K. (2024). Explorando os limites da aprendizagem por reforço profundo em ambientes simulados: um estudo sobre negociação de ativos financeiros e dimensionamento de lotes. Doctoral Thesis, Escola Politécnica, University of São Paulo, São Paulo. doi:10.11606/T.3.2024.tde-26082024-093343. Retrieved 2024-08-31, from www.teses.usp.br

3. L. Felizardo, E. Fadda, P. Brandimarte, E. Del-Moral-Hernandez "Reinforcement learning approaches for the stochastic discrete lot-sizing problem on parallel machines" Expert Systems with Applications Volume 246, 15 July 2024, 123036DOI: https://doi.org/10.1016/j.eswa.2023.123036

4. D. Gioia, L. Felizardo, P. Brandimarte, "Simulation-Based Inventory Management of Perishable Products Via Linear Discrete Choice Models", Computers & Operations Research September 2023, DOI: https://doi.org/10.1016/j.cor.2023.106270

5. L. Felizardo, "Reinforcement Learning Applied to Trading Systems: A Survey",preprint available at Arxiv, December 2022, arXiv preprint arXiv:2212.06064

6. L. Felizardo, E. Urbinate, E. Del-Moral-Hernandez "Deep learning stacking for financial time series forecasting: an analysis with synthetic and real-world time series", 2022: Anais do XIX Encontro Nacional de Inteligência Artificial e Computacional, 28 November 2022, DOI: https://doi.org/10.5753/eniac.2022

7. L. Felizardo, E.Y. Matsumoto, E. Del-Moral-Hernandez, "Solving the optimal stopping problem with reinforcement learning: an application in financial option exercise", 2022 International Joint Conference on Neural Networks (IJCNN), 18-23 July 2022, DOI: 10.1109/IJCNN55064.2022.9892333

8. L. Felizardo, F. Paiva, E.Y. Matsumoto, C. de-Vita-Graves,A. Realli, E. Del-Moral-Hernandez, "Outperforming algorithmic trading reinforcement learning systems: A supervised approach to the cryptocurrency market", Expert Systems with Applications, Volume 202, 15 September 2022, 117259, DOI: https://doi.org/10.1016/j.eswa.2022.117259

9. D. Gioia, L. Felizardo, P. Brandimarte, "Inventory management of vertically differentiated perishable products with stock-out based substitution", Manufacturing Modelling, Management and Control - 10th MIM 2022, DOI: https://doi.org/10.1016/j.ifacol.2022.10.115

10. F. Paiva, L. Felizardo, A. Realli, R. Bianchi, "Intelligent Trading Systems: A Sentiment-Aware Reinforcement Learning Approach", 2021 6th International Conference on AI in Finance (ICAIF), 2021, pp. 1-8, DOI: https://doi.org/10.1145/3490354.3494445

11. L. Felizardo, R. Oliveira, E. Del-Moral-Hernandez and F. Cozman, "Comparative study of Bitcoin price prediction using WaveNets, Recurrent Neural Networks and other Machine Learning Methods",2019 6th International Conference on Behavioral, Economic and Socio-Cultural Computing (BESC), 2019, pp. 1-6, doi: 10.1109/BESC48373.2019.8963009

12. L. Felizardo, A. Pinto, "A Study on Neural Network Architecture Applied to the Prediction of Brazilian Stock Returns", 2017 Encontro da Associação Nacional de Pós-Graduação e Pesquisa em Administração (EnANPAD), 2017, arxiv: https://arxiv.org/abs/1901.09143