System optimization · TradersWeek

Skip to main content

Output: Signal
Input: Rule inputs, market state and execution constraints
Horizon: The system holding period
Best use: Make entry, exit and abstention rules testable as one procedure.

Input: Rule inputs, market state and execution constraints.
Output: signal.
Use boundary: Make entry, exit and abstention rules testable as one procedure.

The graph7

How the method is built, and where it has been read

Depends on

Often reviewed together

Seasonal trading5 readings

Often reviewed together

Relative Strength Index6 readings

Often reviewed together

Moving average8 readings

Often reviewed together

Rule-based entry9 readings

Often reviewed together

Robustness testing26 readings

Often reviewed together

Walk-forward analysis28 readings

Often reviewed together

Mechanical trading system35 readings

Read in the archive24 of 131 readings

1984Evaluating mechanical systems beyond net profitSystem design 1986Degrees of freedom in trading system optimizationSystem design 1987Relative strength evaluation under competing optimization criteriaIndicators and filters 1987Mechanical systems need more than pretty chartsSystem design 1987Evaluating silver moving averages and RSI by scoring ruleIndicators and filters 1988Walk-forward and neighborhood tests after optimizationSystem design 1988Simple systems over optimized complexitySystem design 1988Undisclosed rules block system robustness testsSystem design 1988Two-sided optimization for volatility-scaled breakout rulesSystem design 1988Testing re-optimization calendars against random parameter controlsSystem design 1988Cycle rule inputs until the parameter search stopsSystem design 1989Binary search limits on multi-peak average gridsSystem design 1989Four-span MACD lookbacks as perishable parametersIndicators and filters 1989Evaluate an always-in ATR breakout as one procedureTrend and mean reversion 1989Constructing holdout-checked synthetic prices from chaos mapsTime series and forecasting 1989Parameter neighborhoods that survive a shiftSystem design 1990Curve fits fail the forecast testTime series and forecasting 1990Use profit mapping to keep a cycle and stop plateauSystem design 1990Three-window walk-forward system evaluationSystem design 1990Why popular indicator optimization fails robustnessSystem design 1990Building the construction layer of a mechanical trading systemSystem design 1990Cycle-tested five-year fund rank rotationPortfolio construction 1990Split-sample tests for stochastic parameter gridsIndicators and filters 1991Constructing a mechanical crossover on a synthetic price seriesSystem design

This registry entry describes a research method. It is not investment advice and does not make a performance claim.