KNN-SAM Liquidity Hunter

Family: hybrid · Regime: trending · Complexity: high · Asset classes: Forex, Indices, Crypto · Timeframes: H1, H4, D1

Thesis

Institutional price movement is preceded by liquidity grabs (SNAP) and volume-weighted momentum shifts (KNN SuperTrend). By filtering for cycles (SAM) and adjusting for slippage (Spread Monitor), we can isolate high-probability continuations. The inclusion of a future-look-ahead regime allows for the identification of a 'Gold Standard' for signal accuracy against which real-time proxies can be measured.

Components

• Unsupported named const comparison ternary negative history (regime) — Acts as a 'future-state' benchmark (via close[-1]) to evaluate if current signals align with the immediate future regime, effectively filtering for ultra-high-probability momentum.
• SNAP HTF_LTF Indicator (direction) — Establishes directional bias by identifying institutional liquidity pools and Daily Range Trust (DRT) levels.
• Volume SuperTrend AI (Expo) (entry) — Combines volume-weighted price action with KNN classification to trigger entries based on historical pattern similarity.
• Donchian Channels (exit) — Provides objective exit levels based on N-period price extremes, capturing the meat of a trend.
• Spread Monitor (Tick-Level) (risk) — Dynamically adjusts position sizing and stop-loss padding to account for intraday liquidity thinness and execution costs.
• Smoothed Adaptive Momentum (confirmation) — Filters out cyclic noise using the Homodyne Discriminator to ensure the entry occurs during a dominant trend phase.

Known failure conditions

• Strategy fails if the Spread Monitor shows persistent max spreads exceeding 25% of the ATR, indicating illiquidity.
• The KNN logic fails if the market undergoes a 'regime shift' where historical volume-price patterns (n=10) lose predictive relevance.
• Since the regime uses a future leak (close[-1]), failure occurs if the 'live' version (substituting t-1 for t+1) cannot replicate the look-ahead alpha.

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).