KNN-Volume Matrix Momentum Strategy

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

Thesis

The strategy hypothesizes that market trends are most tradeable when volume-weighted momentum (Volume SuperTrend AI) aligns with price equilibrium (Ichimoku) and is confirmed by accelerating momentum (MACDO). By entering only on retests of pivot-based support/resistance clusters (SML), the strategy exploits the behavioral tendency for price to react to historical 'value' areas before resuming a trend. The KNN component serves as a 'memory' filter to ensure current price behavior mimics historically successful trend phases.

Components

• Volume SuperTrend AI (Expo) (regime) — Filters for high-conviction trends where volume and price proximity (via KNN) suggest institutional participation rather than retail noise.
• Ichimoku Kinko Hyo (direction) — Ensures the higher-order trend and market equilibrium are aligned before considering local entries.
• SML — SUPPORT/RESISTANCE MATRIX (entry) — Provides the specific price levels (retests of pivot clusters) where entries are executionally viable.
• ADX / Connectable [Azullian] (exit) — Monitors trend exhaustion to trigger exits before a full reversal occurs.
• SuperTrend & Pivots (risk) — Uses daily structural levels (Pivots) and volatility-based trailing stops for risk management.
• Moving Average Convergence/Divergence Oscillation (MACDO) (confirmation) — Tracks the 'momentum of momentum' to ensure the entry occurs at a point of accelerating price velocity.

Known failure conditions

• The KNN algorithm fails to classify trends distinctly in sustained low-volatility 'grinds'.
• Price repeatedly pierces SML zones without reacting, indicating a breakdown in structural relevance.
• MACDO oscillates rapidly around zero, generating excessive noise signals.

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.