About this course
Combines quantitative finance with machine learning in Python. Delegates work with market data in pandas, compute returns and risk measures, build Markowitz portfolios, estimate CAPM betas, price options with Black-Scholes and Monte Carlo simulation, and calculate value at risk. Later sessions apply machine learning and reinforcement learning to return prediction and trading strategies, with rigorous backtesting.
Why this course
Treasury, investment and risk teams increasingly need staff who can build and test their own quantitative models rather than depend on vendor software. Combining financial theory with machine learning lets analysts evaluate strategies properly, spot overfitted backtests and quantify risk. This supports better reserve management, portfolio decisions and model risk oversight.
What delegates will be able to do
By the end of the course, delegates will be able to
- Calculate returns, volatility, correlations and value at risk from market data in Python
- Construct mean-variance optimal portfolios and plot the efficient frontier
- Price European options using Black-Scholes and Monte Carlo simulation
- Build machine learning models to forecast returns and classify market regimes
- Backtest a trading strategy and identify sources of overfitting and bias
Who should attend
Quantitative analysts, treasury and reserve management staff, portfolio managers, risk analysts and economists in central banks, commercial banks and asset managers. Delegates need working Python skills and a grounding in finance and statistics.
How it is delivered
Coding labs in Python using real market data, with worked financial models, portfolio and risk exercises and a group strategy backtesting project. It is available as a public course, in-house at your premises, or as live virtual sessions. Duration and dates are confirmed in your quote, and in-house groups can have the examples and exercises fitted to their organisation.