TOKT11141 — TOKT11141

This course develops a problem-driven framework for applying machine learning to quantitative finance. It begins with the financial decision, classical benchmark, information set, and evaluation criterion before introducing a machine-learning extension. Students learn the common machine-learning toolkit required for financial applications and then apply it, in the same sequence as the course textbook, to return prediction and trading signals, portfolio construction, financial risk management, and derivative pricing and hedging. Particular emphasis is placed on point-in-time data, chronological validation, benchmark-first model comparison, transaction and hedging costs, financial consistency, and the distinction between predictive accuracy and economic value.

• Introduction to quantitative finance and credible data-driven financial research
• Machine-learning fundamentals for quantitative finance
• Return prediction and trading signals
• Machine learning for portfolio construction
• Machine learning for financial risk management
• Machine learning for derivative pricing and hedging