Polynomial Regression Breakouts with a Volatility-Angle Filter

Summary

This strategy fits polynomial regression forecasts to recent highs and lows, then counts how often observed prices cross those forecasts. When the count reaches a threshold, it treats the move as a possible emerging trend and considers a long or short entry. A volatility-angle condition is also used to avoid trading in choppy conditions. Stop-loss and take-profit levels are set through percentage inputs; the listed defaults are 1.4% and 5.6%, respectively.

The document presents the method as a rules-based way to identify trend changes, but supplies no performance results or comparison against a benchmark. It explicitly warns that parameter tuning can overfit and that results may depend on the market and timeframe. Its example backtest uses BTC/USDT futures on a four-hour chart for part of 2023. The source also contains apparent inconsistencies between the narrative and implementation, including signal logic and date inputs, so the described method should not be assumed to match the code exactly. It calls for testing across assets, timeframes, and market conditions.

Key ideas

• The method uses polynomial regression forecasts of recent highs and lows as reference levels.
• Counts of price movements beyond those forecasts are used to trigger potential directional signals.
• A volatility-angle filter and percentage stop and target inputs are part of the described system.
• The document cautions that parameter optimization can overfit and that market conditions affect performance.
• The example identifies a futures instrument and timeframe but reports no backtest results.

Tags

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