Optional Advanced Modules

These modules are for experienced learners who have completed the core parts of the course and want depth in a specific area. Each module is self-contained: it states its own prerequisites, and no core lesson depends on any of them. Take the ones relevant to the roles or markets you are targeting — an execution researcher needs the impact and Almgren–Chriss modules; someone heading toward derivatives desks needs stochastic calculus and options pricing; nobody needs all thirteen.

Module	Focus
Bayesian Optimization for Hyperparameters	Sample-efficient parameter tuning without overfitting
Particle and Kalman Filters	State-space models, dynamic hedge ratios, non-Gaussian filtering
Stochastic Calculus	Brownian motion, Itô calculus, SDEs, continuous-time models
Optimal Execution: Almgren–Chriss	Implementation shortfall and optimal trade scheduling
Market Impact Models	Temporary vs permanent impact, square-root law, estimation from fills
Reinforcement Learning for Execution	Where RL actually works in trading
Alternative Data	NLP, satellite, filings; point-in-time hygiene and vendor evaluation
GPU Acceleration with CUDA	CuPy, Numba, GPU-accelerated backtests and training
Distributed Backtesting	Ray/Dask parameter sweeps without distributed overfitting
High-Performance Computing	Python's limits, Cython/Rust extensions, profiling at scale
Options Pricing	Black–Scholes, Greeks, the implied volatility surface
Market Making	Inventory models, quoting, adverse selection
Crypto Market Microstructure	Perpetuals, funding, fragmented venues, 24/7 operations