Hyejin Ku

Short Bio

Hyejin Ku is a Full Professor in the Department of Mathematics and Statistics at York University. Her research spans mathematical finance, machine learning, and reinforcement learning, with a focus on risk-sensitive decision-making. She has supervised multiple PhD and Master’s students, with publications in leading venues such as ICML and Expert Systems with Applications. Her work bridges theory and practice, contributing to the development of reliable learning methods under uncertainty across domains including finance and operations.

Research Interests

Risk-Sensitive Reinforcement Learning, Mathematical Finance, and Machine Learning

My research lies at the intersection of risk measurement, decision-making under uncertainty, and machine learning. I focus on developing principled, mathematically grounded models for risk-sensitive reinforcement learning, optimal policy learning, portfolio optimization, and credit risk assessment. These efforts aim to advance both theoretical understanding and practical methodologies for sequential decision-making under risk.

In a recent project, we proposed a novel Distributional Reinforcement Learning (DRL) algorithm that optimizes a broad class of static spectral risk measures. The method offers theoretical convergence guarantees and interpretable policies through coherent risk decomposition. Empirical results show improved performance over existing risk-neutral and risk-sensitive models on benchmark environments.

Previous work includes ensemble learning models for credit rating prediction using real-world financial data and sequence-based clustering of firms for long-term credit risk assessment. These projects integrate AI techniques with domain-specific modeling to enable robust, data-driven decision-making in high-stakes financial contexts.

Sub-Disciplines

Mathematical Finance, Reinforcement Learning

Research Areas