김우창 연구실

Integration of machine-learning techniques to financial problems, focusing on deep reinforcement learning for sequential decision making. Applications include optimal high-frequency trading policy development and portfolio optimization under constraints.

Technology-driven financial services aimed at democratizing asset management. Development of personalized life-cycle goal-based investment services with focus on scalability and computational efficiency.

Quantitative technologies for improving investment performance through modeling uncertainties and obtaining optimal investment decisions. Focus on dynamic asset allocation and regime switching frameworks.

Study of financial optimization problems including robust optimization, stochastic programming, and dynamic programming from the perspective of optimal decision making under uncertainty.