Who it is for
Systematic traders, software developers, and quantitative finance practitioners wanting automated execution.
Advanced
Algo Trading
Rule-based algorithmic trading: Python data pipelines, strategy backtesting, execution slippage, broker API connectivity, and automated risk guardrails.
Modules
- Python for market data: NumPy and pandas
- Statistics before any model
- Machine learning: features, a hold-out test, and overfitting
- Algorithmic rules: data, entry, size and exit
- Backtests with costs and slippage
- Broker connectivity, WebSockets and the order lifecycle
- Automated risk limits and a kill switch
Course structure
Python, machine learning and algorithmic trading sit in every program as methods. Depth follows the subject. They are not a return.
Python
Work that needs a calculation is done in Python. Load a table, state the assumption, and compute the result with NumPy and pandas. A notebook is a worksheet. It is not a signal.
Machine learning
A model is a function fit to past data. The class covers features, a split between the data you fit and the data you score, and why a fit on history is not something you can spend. It is a method, not a tip.
Algorithmic trading
A strategy is a rule a computer can follow: data, entry, size, exit, and a hard risk stop. A test includes costs. The execution lab is the Algo Trading program. Every other program uses the same standard: write the rule before any code.
You leave with
- Build an event-driven backtesting and execution engine in Python
- Connect to live broker APIs via WebSockets and REST for automated order routing
- Implement automated risk controls, hard stop-losses, and circuit breakers