KNN-Filtered SuperTrend with Trailing Profit and Stop Levels

Summary

This strategy combines a conventional ATR-based SuperTrend with a nearest-neighbor filter and trailing take-profit and stop-loss levels. It keeps historical SuperTrend values that match the current direction and fall within distance bounds derived from smoothed fast and slow data, then averages the selected values. The average may use a simple or exponential method. Exits are intended to capture gains during strong moves while limiting exposure when the trend reverses.

The description explains the trade-off: choppy consolidation can trigger repeated direction changes and small losses, while sustained momentum may produce larger gains. It illustrates how a profit target can close a position before price retraces to the SuperTrend and notes that the machine-learning filter can make the line and target jagged. The author cites differing historical profit figures for two stop settings, but supplies no systematic test design or evidence of robustness. Results depend on parameters and market conditions, and past performance does not establish future results.

Key ideas

• The strategy filters historical SuperTrend values by direction and nearest-neighbor distance before averaging them.
• The filtered SuperTrend is paired with trailing profit and stop levels to manage exits.
• Frequent signal reversals during consolidation can produce multiple small losses.
• Strong momentum may allow larger gains, but the document does not establish reliable future performance.

Tags

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