KNN-Fractal Institutional Displacement Strategy

Family: hybrid · Regime: trending · Complexity: high · Asset classes: FX, Indices, Crypto · Timeframes: H1, H4

Thesis

Market shifts occur when HTF liquidity is swept and followed by institutional displacement (FVGs). By using a KNN-weighted volume trend to identify the dominant regime and an HP filter to avoid entering at cyclical extremes, we can capture the meat of a structural reversal timed by a momentum reset (Stochastic). This edge exists because retail traders often enter on the first sweep, while institutional order flow is confirmed only after the subsequent impulsive displacement.

Components

• Volume SuperTrend AI (Expo) (regime) — Acts as the primary trend filter, using KNN to classify historical volume-weighted trends to avoid 'whipsaw' in low-conviction regimes.
• Open Source Fractal Model (direction) — Identifies High Timeframe (HTF) liquidity sweeps and Change in Sub-structure (CISD) to establish a directional bias based on institutional order flow.
• Stochastic Oscillator (entry) — Provides the final execution trigger, timing the entry on a momentum reset after the higher-level structural conditions are met.
• Ichimoku Kinko Hyo (exit) — Used for dynamic profit taking and trend exhaustion detection via the Kumo (Cloud) and Tenkan/Kijun crosses.
• Equity Line Projection (risk) — Translates the distance between entry and the Fractal-defined stop-loss into a projected equity impact to determine precise position sizing.
• Order Block / FVG Detector (confirmation) — Confirms the fractal shift by detecting impulsive displacement (Fair Value Gaps) which indicates institutional participation.
• Hodrick-Prescott Filter (HP) (volatility_filter) — Decomposes price into a trend and cycle; the cyclical component is used to ensure the entry is not made at a cyclical peak (for longs) or trough (for shorts).

Known failure conditions

• Price reaches the HTF sweep level without forming an OB/FVG, indicating a continuation rather than a reversal.
• The HP cycle component remains flat for >20 bars, suggesting a low-volatility environment where Stochastic signals are noise.
• Equity Line Projection reveals that the required stop-loss distance would require a lot size below the broker's minimum for the target risk %.

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