Skip to main content
Track System optimization
23 / 23
Library

20251-52

Joint channel design with a trend filter and stop-loss orders

The archive builds a price channel from a linear-regression centerline and its largest deviations, then writes slope permission, a band-edge flatten, and a shared search as one procedure. Futures size is set before entry from a fixed notional and a 20-day average true range; equity tests stay long-only on the next open.

  • A channel can be built from a linear-regression centerline plus the largest deviations above and below that line, using close, typical price, or the high-low midpoint.
  • The sign of the regression slope can serve as a Trend filter, while a close through the opposite band can flatten a position before the slope reverses.
  • Slope-as-trend, band-breakout, and inside-band rules can be selected as alternative rule sets inside a single System optimization procedure covering entry, exit, and abstention.
  • Averaging every tested lookback, rather than keeping only the single best cell, can be used as a robustness check on the whole procedure.
Entries in this reading3 entries

From a channel to a joint procedure

The archive builds a price channel and then writes a Trend filter, a Stop-loss order, and System optimization inside a single test procedure.

How the channel is built

A channel can be built from a linear-regression centerline plus the largest deviations above and below that line. The input series can be the close, typical price, or the high-low midpoint.

Permission from the slope

The sign of the regression slope can serve as a Trend filter that permits long exposure when the slope is positive and short exposure when it is negative.

A stop at the channel edge

A close through the opposite band can flatten a position before the slope itself reverses, placing a loss bound at the channel edge. That bound is the Stop-loss order in this workflow.

One procedure for entry, exit and abstention

Slope-as-trend, band-breakout, and inside-band rules can be selected as alternative rule sets inside a single test procedure covering entry, exit, and abstention. That joint writing is System optimization.

The shared search space can include regression lookbacks from 20 to 150 observations and, for inside-band trades, buy and sell zones from 5% to 50% of channel width.

Inside-band entries can require the slope to agree with the trade, while exits trigger at the opposite zone or when the slope changes sign.

Exposure, timing and robustness

Futures exposure can be sized from a fixed notional divided by a 20-day average true range times the contract point value, so stop distance and size are set before entry.

Averaging every tested lookback, rather than keeping only the single best cell, can be used as a robustness check on the whole procedure.

Equity tests can be constrained to long-only entries on the next open, while futures tests can allow both directions on the current close.

Educational research material, not investment advice. Historical source context does not establish present-day performance.
23 of 23 in the System optimization track
1984Track finished · Next track: TRIXConstructing TRIX from a cutoff to one shared alpha30 readings
All readings on this track · 23 readings
  1. 1984Evaluating mechanical systems beyond net profit
  2. 1987Mechanical systems need more than pretty charts
  3. 1987Evaluating silver moving averages and RSI by scoring rule
  4. 1988Simple systems over optimized complexity
  5. 1988Cycle rule inputs until the parameter search stops
  6. 1990Split-sample tests for stochastic parameter grids
  7. 1993Four-subsystem trading system construction
  8. 1993Randomized price paths for stock system parameters
  9. 1994Mechanical timing with out-of-sample and filter checks
  10. 1995Evaluating asymmetric percent-reversal trading rules
  11. 1996Evaluating a daily volume-strength and new-high new-low timing procedure
  12. 1997Rule-based intraday system design with genetic search
  13. 1997Evolving three-rule systems with genetic templates
  14. 1997Audit the holdout and the exposure before the fitted entries
  15. 2001Inner weights are part of the candlestick signal
  16. 2003Mechanical short-term rules for news-sensitive rallies
  17. 2004Band construction as a testable trading procedure
  18. 2006Layered day-session automation from brackets to rules
  19. 2006Why mechanical rules must be retuned per security
  20. 2006A linear-regression next-bar forecast needs a searchable cutoff
  21. 2015Construct if-then rules, then backtest and optimize
  22. 2015Mechanical system design as a critique of discretion
  23. 2025Joint channel design with a trend filter and stop-loss orders
All 131 readings tagged System optimization
Also on System optimization5 readings