Skip to main content
Track Robustness testing
55 / 57
Search the archiveLibrary
Library

2020issue C0348-55

Hidden optimization in ported relative-strength systems

A platform recode of a zero-cross relative-strength hold is already a new procedure when it adds exits, borrowed defaults, or in-sample knobs. Those changes are system optimization, so robustness testing and walk-forward analysis still belong in the workflow before the rules are taught as one method.

  • Entry, exit, and abstention all use a second market series, so the published signal is a relative-strength rule rather than a single-symbol price rule.
  • Replacing a fixed hold with oscillator exits, or opening the same rule inputs to an in-sample search, turns a port into a new optimization surface.
  • A companion critique treats hidden defaults as earlier system optimization and says an untouched default set is not automatically more trustworthy than a later version.
  • Editorial reading: keep the initial version for research, then put later versions through robustness testing and walk-forward analysis before treating future use as better supported.
Entries in this reading3 entries
Current trackRobustness testing67 readingsSystem optimization93 readingsWalk-forward analysis100 readings

What the ports compute

Several implementations compute the oscillator as 100 times an exponential average of the change in the log close ratio versus a reference series, using a 90-bar difference and 3-bar smoothing.

The baseline long-only procedure buys when that oscillator crosses above zero and exits after a fixed hold. Some ports write the hold as 180 bars. Others write it as nine 21-bar months.

Entry, exit, and abstention all require a second market series as the comparison input, so the signal is a relative-strength rule rather than a single-symbol price rule.

RSMK on AMZN from the TradersStudio port, 2009–2013

A trader using this port is still making a zero-cross bet: RSMK on AMZN ran above zero through most of 2009–2011, then broke down to the scale floor in mid-2012 and crossed below zero again in 2013. Numbers were read from the plotted oscillator on the TradersStudio screenshot against its labeled RSMK scale, not from a published table.
A trader using this port is still making a zero-cross bet: RSMK on AMZN ran above zero through most of 2009–2011, then broke down to the scale floor in mid-2012 and crossed below zero again in 2013. Numbers were read from the plotted oscillator on the TradersStudio screenshot against its labeled RSMK scale, not from a published table.AMZN · daily · 2009-01-01T00:00:00.000Z to 2013-08-31T00:00:00.000Z

The published port uses a 90-bar lookback and a 3-bar EMA versus the reference series. Digitized readings are approximate to a few indicator points; the pane does not support finer precision.

One recode replaces the calendar hold with three oscillator exits: a 20-point drop from a 20-day high, a cross below a 20-day exponential average, and a return through zero. It marks those periods and point thresholds as search inputs.

At least two ports invite an in-sample search over the same rule inputs, which turns the published defaults into an optimization surface rather than a fixed procedure.

Hidden defaults and later versions

A companion critique states that almost every strategy is optimized to some degree, including hidden defaults such as an ADX length of 14 and a trend threshold of 20 that were themselves chosen after earlier study.

That critique holds that a small rule change means the procedure is no longer the initial version, and that an apparently untouched default set should not be assumed more trustworthy than a later version.

The prescribed response is to keep the initial version for research, still put later versions through a previously proven development process, and only then treat future use as better supported.

Why the later checks still apply

Editorial reading: extra exits, borrowed defaults, and in-sample knobs already count as system optimization. A recode is therefore a new procedure, not a neutral copy of the initial version.

The same robustness testing and walk-forward analysis used for a freshly designed system still apply. Those checks make entry, exit, and abstention rules testable as one procedure before the recode is taught as the method.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
55 of 57 in the Robustness testing track
202041-41 pp.Next on Robustness testingWhen mechanical historical tests decay after optimizationFavorable historical results from a mechanical procedure are not, by themselves, a reliable basis for expecting the same procedure to keep producing favorable results after it is used live.
All readings on this track · 57 readings
  1. 1986Degrees of freedom in trading system optimization
  2. 1988Walk-forward and neighborhood tests after optimization
  3. 1988Undisclosed rules block system robustness tests
  4. 1988Testing re-optimization calendars against random parameter controls
  5. 1989Binary search limits on multi-peak average grids
  6. 1989Parameter neighborhoods that survive a shift
  7. 1990Use profit mapping to keep a cycle and stop plateau
  8. 1990Why popular indicator optimization fails robustness
  9. 1991Retesting weighted indicator balances across horizons
  10. 1992Constructing forecast models with regression, walk-forward, and robustness
  11. 1992Diagnose regimes before you lock parameters
  12. 1992When stops change system timing
  13. 1993Walk-forward halt rules for forecast models
  14. 1994Walk-forward evaluation of genetic index rules
  15. 1995Input pruning as walk-forward system evaluation
  16. 1995Critiquing neural nets as incomplete trading systems
  17. 1996Rebuild the equity-path ratio before it ranks a designed system
  18. 1996Parameter grids can fit random walks
  19. 1996Walk-forward analysis belongs in the design of a mechanical trading system
  20. 1997When a holdout fails, discard the rule set
  21. 1997Test rewarded rule breaks before replacing the system
  22. 1997Walk-forward rules keep system research from rewriting live trades
  23. 1999Keep a channel-breakout to two lookbacks and test neighbor stability
  24. 1999Constant investment size in stock system evaluation
  25. 2000Forcing optimization maps mechanical system failure boundaries
  26. 2000Robust parameter selection with surface charts
  27. 2001A two-gate classroom test for a two-window momentum trend filter
  28. 2002How a two-sided continuation factor becomes a testable trend rule
  29. 2002Evaluating two-window trend intensity as a reversal rule
  30. 2003Discounting speculative bubbles in system robustness tests
  31. 2003Walk-forward evaluation of locked stochastic oscillator rules
  32. 2003Critiquing mechanical system design after extreme price regimes
  33. 2004Evaluating a two-window trend trigger
  34. 2005Grade backtested signals with holdouts and optimization plateaus
  35. 2006Reserved-sample evaluation of trading system design
  36. 2006Walk-forward critique of hindsight crossover systems
  37. 2008Condition-matched walk-forward evaluation for mechanical systems
  38. 2011Session-split evaluation of regular and overnight systems
  39. 2012Walk-forward evaluation as operator rehearsal
  40. 2013Two-window evaluation of mechanical trading systems
  41. 2013Walk-forward filter selection for repeated-median velocity
  42. 2014Walk-forward evaluation for fading-memory velocity systems
  43. 2015Test oscillator events before tuning rules
  44. 2016Walk-forward evaluation of a five-parameter parabolic stop-and-reversal
  45. 2016Walk-forward optimization without curve fitting
  46. 2017Optimization without overfitting in trend-system evaluation
  47. 2017Parameter stability is a better guide than a larger crossover grid
  48. 2018Point-in-time universes for system evaluation
  49. 2018Walk-forward robustness evaluation for optimized systems
  50. 2018Critiquing breakout systems through robustness tests
  51. 2018A critique of parameter fitting in system design
  52. 2019Noise-matched rules still need trend filters and robustness tests
  53. 2019Three gates for evaluating a trading system
  54. 2020Data construction as a mechanical system input
  55. 2020Hidden optimization in ported relative-strength systems
  56. 2020When mechanical historical tests decay after optimization
  57. 2025Add a second procedure before you retune the first
By fieldSystem design130 readingsBy year2020100 readings
All 67 readings tagged Robustness testing
Also on Robustness testing5 readings
1986Degrees of freedom in trading system optimization1988Testing re-optimization calendars against random parameter controls1988Walk-forward and neighborhood tests after optimization1992Diagnose regimes before you lock parameters1993Walk-forward halt rules for forecast models