My research focuses on developing advanced machine learning and reinforcement learning methodologies for quantitative finance and algorithmic trading. I lead research initiatives that bridge cutting-edge academic research with practical applications in institutional trading environments.

Research Methodology

My work centers on three core methodological areas:

• Risk-Averse Reinforcement Learning: Developing algorithms that explicitly account for risk and uncertainty in decision-making processes, enabling more robust trading strategies
• Online Learning: Advancing online convex optimization, expert algorithms, and multi-armed bandit approaches for adaptive trading systems
• Online Planning: Leveraging Monte Carlo Tree Search and related planning algorithms for high-dimensional financial decision problems

Applications in Quantitative Finance

I apply these methodologies to solve critical challenges in algorithmic trading and risk management:

• Quantitative Trading: Developing systematic strategies that generate alpha while maintaining low correlation with market factors
• Portfolio Optimization: Designing multi-period portfolio allocation frameworks that account for transaction costs and market dynamics
• Market Making: Creating dynamic pricing policies for continuous asset pricing in dealer markets
• Optimal Execution: Developing execution strategies that minimize market impact while achieving execution objectives
• Derivatives Hedging: Advancing beyond traditional delta hedging through adaptive, risk-aware hedging strategies

Impact and Applications

My research has been applied in production trading systems and has contributed to the development of systematic trading strategies at leading financial institutions. The methodologies I develop address real-world constraints including transaction costs, market impact, and regulatory requirements.

Publications and Resources

For detailed information on my research contributions, please see my publications. My Ph.D. dissertation, Augmenting Traders with Learning Machines, provides a comprehensive overview of my research program and can be found here.

For foundational reading on reinforcement learning, I recommend Sutton & Barto’s textbook, which provides the theoretical foundation for much of this work.