Student Supervision

Mentoring Philosophy

My mentoring philosophy centers on integrating mathematical rigor with the practical and computational applications of these concepts in quantitative finance and data science. My goal is to equip students with the analytical skills needed for advanced study and industry innovation.

For both graduate and undergraduate students, my mentorship style is structured to foster independent, high-impact research and comprehensive professional development.

Key Mentorship Goals

• Rigorous Foundation: Ensuring students master the theoretical underpinnings required for high-level research in mathematical finance and data science.
• Problem-Driven Approach: Encouraging students to identify, formulate, and mathematically model open problems in cutting-edge areas of their own interest, particularly in Decentralized Finance (DeFi).
• Professional Development: Providing guidance on academic, and cultivating professional practice skills applicable to both academia and industry.

Current Research Groups

I currently supervise and lead three active research groups, emphasizing collaborative and project-driven learning.

• Quantitative Trading & Hedging: This group focuses on developing and implementing machine learning models for trading various financial instruments (e.g., stocks, futures, options).
• Decentralized Finance (DeFi) Modeling: This group explores the mathematical and computational aspects of DeFi, including modeling Automated Market Makers (AMMs) (e.g., Uniswap, Curve), analyzing liquidity provider rewards, and optimizing complex yield farming strategies.
• Computational AI & High-Performance Computing (HPC): This group utilizes JAX to conduct high-performance numerical computations and implement state-of-the-art AI algorithms (e.g., Distributional Reinforcement Learning) for theoretical and practical applications in real world.

Graduated Theses

Wei-Ru Chen (M.S., Co-advised with Yuki Chino)

• Thesis Topic: A Study of AMM Mechanisms and Liquidity Provider Rewards
• Completion Date: June 2024
• Thesis Document

🔬 Undergraduate Research Projects

I actively mentor undergraduate students through competitive programs and independent projects, focusing on practical data science and quantitative finance applications.

2025-2026 NCTS Research Program

• Students: Hai-Ching Shih
• Topic: A Clustering Framework for Identifying On-Chain Behavioral Patterns in Automated Market Makers

2024 Project: Predictive Modeling for Vehicle Allocation

• Project Title: Predictive Modeling for Optimized Vehicle Allocation and Routing in Postal Delivery
• Students: Shih-Bin Chen, Jie-Hong Lai, Jia-Wei Liao, Yuan-Hong Lin
• Awards: Best Application Award & GLORY Data Application Innovation Award (Postal Big Data Competition, 2024)
• Project Notes

2024 NCTS Summer Research Program

• Co-Advisor: A. Christian Silva
• Students: Tzu-Ling Hsieh, Guan Ting Lu, Tai-Jun Lai, Mu-Chian Lin
• Topic: Optimization Methods in Quantitative Trading
• Project Notes

2023-2024 NCTS Research Program

• Co-Advisor: Chang-Ye Tu
• Students: De-Jin Huang, Chen-Chung Yang
• Topic: Deep Hedging: Applying deep learning techniques to derivative hedging strategies.
• Project Notes

2023 Independent Project: Time Series Generation

• Project Title: Sig-Wasserstein GANs for Time Series Generation
• Student: Hua-Hsuan Shih
• Current Position: Master’s student at Columbia MSFE (Master of Science in Financial Engineering)
• Project Repository