I’m a Master’s student in Chemical Engineering at Cornell University in the @varnerlab. My research is centered on sequential decision-making under uncertainty. I develop and apply models like Hidden Markov Models (HMMs), Markov Decision Processes (MDPs), and Reinforcement Learning to tackle complex challenges in quantitative finance, power systems, and chemical process control.
- Core Methods: Hidden Markov Models (HMMs), Markov Decision Processes (MDPs), and Reinforcement Learning (RL).
- Specialized Topics: Multi-Armed Bandits & Contextual Bandits for adaptive decision-making.
- Applications:
- Quantitative Finance: Algorithmic trading, volatility modeling, and market simulation.
- Engineering Control: Optimal control and optimization for power systems and chemical processes.
- Tools & Techniques: Stochastic modeling, time-series analysis, and numerical optimization in Julia & Python.
- Advanced methods in mathematical optimization, including Linear Programming (LP), Nonlinear Programming (NLP), and Mixed-Integer Linear Programming (MILP).
- Techniques for decision-making under uncertainty, such as Stochastic Programming (SP) and Robust Optimization (RO).
- The theory and algorithms for solving large-scale problems, from Dynamic Programming to global optimization solvers.
- Implementing and solving complex optimization models using modern algebraic modeling languages like Pyomo
- Open-source Julia/Python libraries for Reinforcement Learning in financial markets.
- Applying contextual bandits to real-world optimization or control problems.
- Developing control frameworks for chemical processes or power grids using MDPs.
- Research projects exploring the intersection of stochastic modeling and quantitative trading.