Strategy #0000000115 · Computational strategy search
Evolved technical rules and out-of-sample tests
Enter in/out-of-sample returns, turnover, cost per turnover, rule complexity and a validation threshold.
Genetic algorithms or programming search trees of indicators, comparisons and logical operators, selecting, crossing and mutating rules by fitness. Larger search spaces intensify data snooping; reserve untouched time-ordered tests, include costs and record the search. Allen and Karjalainen find no robust US equity excess return after costs for their evolved rules.
No genetic search, data split or multiple-testing correction is performed; assumed figures are not strategy performance.
Three ways in
Understand the story. Then inspect the risk.
Start with a familiar situation, check the payoff, then test how the numbers change.
The idea · in two minutes
After complexity and costs, does in-sample performance generalise beyond an out-of-sample threshold?
Genetic algorithms or programming search trees of indicators, comparisons and logical operators, selecting, crossing and mutating rules by fitness. Larger search spaces intensify data snooping; reserve untouched time-ordered tests, include costs and record the search. Allen and Karjalainen find no robust US equity excess return after costs for their evolved rules.
Enter in/out-of-sample returns, turnover, cost per turnover, rule complexity and a validation threshold.
No genetic search, data split or multiple-testing correction is performed; assumed figures are not strategy performance.
- Input assumptionsEnter in/out-of-sample returns, turnover, cost per turnover, rule complexity and a validation threshold.
- Model outputNo genetic search, data split or multiple-testing correction is performed; assumed figures are not strategy performance.
Illustrative research examples only. They are not live signals or a recommendation.
The mechanics · payoff and exposure
Fitness=R_{train}-C_{turnover}-\eta\cdot Complexity
In/out-of-sample returns and complexity are scenario inputs; no evolutionary search or historical backtest is run.
Greeks: the directional intuition
- 模型
- Measures sensitivity to implied volatility.
- 樣本
- Measures sensitivity to implied volatility.
- 執行
- Measures sensitivity to implied volatility.
Fitness=R_{train}-C_{turnover}-\eta\cdot Complexity
Practical context · published observations
Evolved technical rules and out-of-sample tests: read the record with its caveats.
The chart uses the published figures or explicitly labelled study inputs below. A historical index or model replay is not the same as an investor’s realised account return.
No genetic search, data split or multiple-testing correction is performed; assumed figures are not strategy performance. Source ↗ · Methodology ↗
Change assumptions and inspect the scenario
Inputs illustrate the strategy mechanics; they are not live quotes, forecasts or investment advice.
Variants · same family, different risk levers
Model definitions, data splits and implementation costs affect results.
Compare methodology and execution assumptions.
| Related strategy | Relationship | What changes | New cost or risk |
|---|---|---|---|
| Base scenario | Manual inputs | Genetic algorithms or programming search trees of indicators, comparisons and logical operators, selecting, crossing and mutating rules by fitness. Larger search spaces intensify data snooping; reserve untouched time-ordered tests, include costs and record the search. Allen and Karjalainen find no robust US equity excess return after costs for their evolved rules. | No genetic search, data split or multiple-testing correction is performed; assumed figures are not strategy performance. |
| Conservative version | Lower risk | Raise cost assumptions and cap exposure or search space. | May reduce model adaptability. |
| Validation version | Out-of-sample test | Freeze rules before evaluating untouched data. | Needs more data and governance. |
No genetic search, data split or multiple-testing correction is performed; assumed figures are not strategy performance.
Read beyond the summary
References
Primary sources and research used to describe the strategy and its limits.