Biography

I am a Ph.D. student in Computational and Applied Mathematics at Old Dominion University, specializing in machine learning, statistical theory, and large-scale optimization. Accelerating my academic path, I completed both a B.S. in Economics and Finance and an M.S. in Financial Mathematics within four years, graduating summa cum laude with a record of scholarships and competitive fellowships. My research portfolio spans multivariate estimation for heavy-tailed distributions, neural network–based optimal control with Runge–Kutta discretizations, and systemic risk modeling in financial markets. I integrate rigorous mathematical analysis with modern machine learning, advancing methods that are both theoretically sound and computationally scalable. I have presented work at professional venues such as the ASA Virginia Chapter Conference, underscoring my commitment to producing research that meets the standards of both academia and industry. Complementing my academic research, I have held roles in investment banking, student-managed funds, and data science, gaining experience in quantitative finance, portfolio optimization, and algorithmic modeling. These experiences give me a unique vantage point: the ability to see how advanced methods translate into real-world impact. My long-term goal is to pioneer research that unifies statistical innovation, machine intelligence, and complex systems to solve challenges in finance, energy, and technology.

Academic Information

Status: PhD Student

Year in Program: 1st

Major/Specialty: Applied Mathematics Major - Machine Learning / Data Science Concentration

Degrees: Bachelors of Science - Economics and Finance - University of Wisconsin Green Bay - May 2024 Master of Science - Financial Mathematics - University of Connecticut - May 2025 PhD - Applied Mathematics - Machine Learning / Data Science - Old Dominion University - Present

Research Areas

Applied Mathematics; Computer Science; Data Science; Engineering; Machine Learning/AI

Research Interests

I develop machine learning methods grounded in numerical analysis and robust statistics for high-stakes problems in finance, technology, energy, and (future) PK–PD. I embed Runge–Kutta discretizations into neural pipelines for stable learning of nonlinear dynamics, and use reinforcement learning and differentiable programming to synthesize control policies that honor system constraints. On the inference side, I focus on heavy-tailed robustness, kernel methods, and uncertainty quantification to handle distribution shift. I am interested in applying such frameworks to include portfolio optimization, systemic stress testing, and market microstructure in finance; forecasting and closed-loop control in technology and decentralized energy systems; and prospective optimal dosing in PK–PD via neural ODEs with safety-aware control. Across domains, my goal is the same: use mathematical structure to make ML systems reliable, interpretable, and ready for high-stakes deployment.

Topical Areas

Applied Computer Science; Applied Mathematics; Artificial Intelligence and Intelligent Systems; Computer Science; Economics and Business; Electrical, Electronic, and Information Engineering; Informatics, Analytics and Information Science; Medical Engineering; Other Biological Sciences; Other Computer and Information Sciences; Other Engineering and Technologies; Performance Evaluation and Benchmarking; Statistics and Probability; Training; Visualization and Human-Computer Systems

Relevant Coursework

Real Analysis Machine Learning and Learning Theory Scientific Computing Probability and Measure Theory Statistical Theory and Modeling

Publications & Research Projects

I am currently working on a research project with Dr. Pokojovy. We explore a deep learning framework to determine optimal policies in control problems, specifically in non-linear dynamical systems.

Faculty Mentor

Michael Pokojovy