KNN-Momentum Convergence Strategy

Family: hybrid · Regime: trending · Complexity: medium · Asset classes: FX, Equities, Indices · Timeframes: H1, H4

Thesis

Market trends are most tradable when local price structure (AI Trend Navigator) aligns with medium-term volatility trends (SuperTrend). By entering on a momentum reset (Average Force zero-cross) within these confirmed states, we filter out low-probability reversals. The edge relies on the assumption that a non-linear 'similarity' check (KNN) provides better regime filtering than a simple moving average.

Components

• AI Trend Navigator [K-Neighbor] (regime) — Identifies the dominant regime by comparing local price structures to historical analogs, acting as a non-linear filter for market state.
• Extrem SuperTrend (direction) — Confirms the directional bias using volatility-adjusted price levels to ensure the entry aligns with broader momentum.
• Average Force (entry) — Triggers entries on momentum 'resets' or zero-crosses, capturing the start of a local impulse within the established regime.
• Heiken Ashi (Standard MT5) (exit) — Provides a noise-filtered exit signal based on trend exhaustion, preventing premature exits during minor retracements.
• ATR Heiken Ashi (risk) — Calculates position size and stop loss based on synthetic smoothed volatility, reducing the impact of outliers.

Known failure conditions

• Persistent sideways/range-bound price action causing SuperTrend whipsaws.
• KNN algorithm failing to find relevant historical neighbors in high-volatility 'black swan' events.
• High correlation between momentum (Average Force) and trend (SuperTrend) leading to late entries in short-lived impulses.

Explore the full interactive blueprint with parameter ranges and evidence on WOBR StrategyVerse, or generate this strategy as an MT4/MT5 Expert Advisor with QuantMogul AI Engine (free download).