1
Rules before results
Define entries, exits, sizing, costs, and timing before inspecting performance.
Lesson · Backtesting and Trading Systems
Backtesting Fundamentals
Use historical data to simulate a defined strategy, separate assumptions from results, and state what a backtest can and cannot establish.
Core concepts
What to understand
Keep each definition operational so it can be implemented and tested.
2
Historical simulation
Apply the same rules consistently across every eligible bar or event.
3
Evidence, not certainty
Use the result to reject weak ideas and estimate behavior, not to guarantee future profit.
Interactive lab
Backtesting Assumptions Lab
Change the market regime, rule parameters, and costs. Compare the strategy result with the market behavior that produced it.
Backtesting Assumptions Lab
Deterministic synthetic educational data · no live market connection
BACKTEST MODEL
Process
Backtest in a fixed order
Do not optimize the conclusion before the test is defined.
Define
Write the hypothesis and exact rules.
Simulate
Apply realistic timing, fills, costs, and accounting.
Evaluate
Review returns, drawdown, trade count, regimes, and stability.
Knowledge check
Check your understanding
Select one answer for each question. Feedback appears immediately.
1. What does a backtest directly measure?
A backtest simulates fixed rules on selected historical data and assumptions.
2. Which item must be defined before reviewing results?
Rules must be defined first so the test is not changed to fit the outcome.
3. A strong historical result is best treated as:
A strong backtest is preliminary evidence, not certainty.
4. A rule completes two trades, +7.5% and −1.1%. Its net return is:
1.075 × 0.989 = 1.0632, so +6.3%. Adding gives +6.4% because it ignores that the −1.1% was taken on a larger account — the lab prints this product under its chart.
Practical rules
- Write the hypothesis before running the test.
- Include realistic costs and execution timing.
- Review performance by market regime, not only overall return.
Common mistakes
- Treating historical profit as a prediction.
- Changing rules after seeing every losing period.
- Ignoring how assumptions created the result.
References
Official reading
The labs are simplified simulations. These sources cover historical performance, data, costs, or execution limitations.
FINRA · Smart Beta—What You Need to Know
Explains that historical backtesting is hypothetical and does not predict future performance.
CME Group · Historical Market Data
Describes historical market data used for market analysis and strategy validation.