Courses & learning
Teaching.
Connecting mathematical foundations with the practice of finance, data science and artificial intelligence.
Programme Director
MSc in Financial Technology
Browse current and previous modules for their focus, public outlines and selected resources. Semester-specific instructions, assessment and materials for current students are issued through NTULearn.
undergraduate & postgraduate
Machine Learning in Finance
A practical introduction to machine learning through financial applications, from data preparation and statistical learning to deep neural networks.
- Data preparation & bias-variance trade-off
- Unsupervised & supervised learning
- Regularisation, trees & ensemble methods
- Deep learning
- Group projects using realistic data
Simulation Techniques in Finance
Simulation methods for financial models and the statistical ideas needed to design, implement and assess them.
- Random-variable generation
- Monte Carlo methods
- Stochastic processes & SDEs
- Variance reduction
- Financial simulation applications
Quantitative Methods in Finance
Quantitative foundations for financial modelling, with an emphasis on investment, portfolio analysis and financial risk.
- Asset dynamics
- Derivatives pricing & simulation
- Portfolio selection
- Empirical portfolio analysis
Machine Learning in Finance
Machine learning for finance students, connecting supervised, unsupervised and deep-learning methods to financial data and projects.
- Data preprocessing
- Unsupervised & supervised learning
- Deep learning
- Financial applications & group projects
Preparatory Lessons for SPMS MSc Students
A common mathematical starting point for incoming MSc students, reviewing the tools needed for quantitative postgraduate study.
- Mathematical foundations
- Linear algebra
- Calculus & differential equations
- R programming
Emerging Topics in FinTech
Emerging topics in financial technology for MSc students in Blockchain. For the current topic selection, assessment and materials, please refer to the programme and NTULearn.
For the current syllabus and course materials, please use the programme information and NTULearn.
Course informationLearning through inquiry
Projects & independent study.
Projects are a place to connect theory, computation and a well-defined problem. My supervision record includes undergraduate projects, independent study, research attachments and doctoral work.
Teaching history
Earlier courses & experience.
Previous NTU courses
AI6123 Time Series Analysis · Spring 2026; MSc in Artificial Intelligence, College of Computing and Data Science; about 100 students.
FN6801/FE8506 Calculus & Linear Algebra · Fall, 2019–2025; MSc in Financial Engineering, Nanyang Business School; about 50 students per class.
MH4501 Multivariate Analysis · Spring, 2017–2018 & 2020–2023; approximately 50 students per class.
MH4510 Statistical Learning and Data Mining · Semester 1, 2016–2019; taught independently in 2016–2018 and with Fedor Duzhin in 2019; approximately 80 students per class.
FF6125 FinTech · MSc in Finance, Nanyang Business School; co-taught with Jin Song in 2020, 94 students.
The Chinese University of Hong Kong · 2011–2016
Best Teaching Assistant Award, Spring 2014 for STAT4005 Time Series.
Tutorial teaching
RMSC4003 Statistical Modeling in Financial Markets: twice, 2011–2012, approximately 80 students per class.
RMSC4007 Risk Management with Derivatives Concepts: three times, 2013–2015, approximately 20 students per class.
STAT4005 Time Series: four times, 2012–2015, approximately 110 students per class.
Postgraduate assessment support
STAT5030 Linear Models: Spring 2016, approximately 15 PhD students.
STAT6102 Stochastic Modelling: three times, 2013–2015, approximately 30 MSc students per class.
STAT6107 Official Statistics and Structural Equation Modeling: twice, 2012–2013, approximately 25 MSc students per class.