TURKS: Tiered Risk Sizing with Trend Hysteresis and Kernel Signals

Summary

The visible portion describes TURKS, a Pine Script strategy that combines a trend-state framework, tiered unit risk, and a Nadaraya-Watson kernel-based sell engine. Its comments specify use of a one-sided, non-repainting kernel variant, with the envelope intended to affect position sizing rather than simply plot reversal signals. The strategy configuration uses fixed quantity, no pyramiding, and orders processed at bar close.

The trend mean is set at 200 bars, and the regime uses five consecutive bars above or below that mean to switch state. Embedded parameter notes argue against optimizing these choices: they cite weak transfer of parameter rankings between sample halves and report overfitting concerns. These notes offer methodological context, but the supplied document ends before the complete rules, sizing logic, performance report, or asset and timeframe are shown. The excerpt therefore cannot establish how the strategy performs or fully explain its risk tiers and kernel exits.

Key ideas

• The strategy combines a trend regime, tiered unit risk, and a Nadaraya-Watson kernel-based sell engine.
• The visible comments specify a one-sided kernel variant intended to avoid repainting.
• The regime switches after a set of consecutive closes above or below a 200-bar trend mean.
• The embedded research notes caution that parameter rankings may not transfer between sample periods and discourage optimization.
• The excerpt is incomplete and gives no full sizing rules or performance results.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.