What you will learn
- Construct a point-in-time dataset and universe that avoids look-ahead and survivorship bias.
- Model transaction costs and design out-of-sample and walk-forward tests.
- Interpret performance metrics and run robustness checks before trusting a result.
Before you begin
Working knowledge of returns, volatility and drawdown, and familiarity with simple rule-based strategies such as moving-average crossovers.
Full lesson list
All lessons are freely available. No enrollment or payment is required.
Point-in-Time Data and the Test Universe
- Timestamp data by when it became known and avoid look-ahead bias.
- Build a historical universe that includes delisted securities.
Costs and Out-of-Sample Testing
- Estimate annual cost drag from turnover and per-trade costs.
- Design an out-of-sample and walk-forward test and count its windows.
Reading Reports and Testing Robustness
- Interpret core performance metrics and their blind spots.
- Apply robustness checks, including outlier removal and sensitivity tests.