KNN Volume-Cycle Convergence Strategy

Family: hybrid · Regime: trending · Complexity: high · Asset classes: Equities, High-Volume FX Pairs, Major Crypto · Timeframes: 1H, 4H, Daily

Thesis

This strategy hypothesizes that sustainable price trends are characterized by a convergence of volume-weighted momentum and cyclical alignment. By using KNN to classify the current volume regime and Ehlers DSP to filter out trend noise, the strategy enters only when a fresh price cycle aligns with institutional volume flow. The VPCI acts as an 'exhaustion' valve, assuming that moves lacking volume confirmation are prone to reversal, allowing for earlier exits than traditional trend-following trailing stops.

Components

• Volume SuperTrend AI (Expo) (regime) — Provides a high-conviction regime filter by combining volume-weighted volatility bands with a K-Nearest Neighbors classifier to detect historical trend persistence.
• PineForge demo (direction) — Acts as the price anchor (y = close) for comparison against the SuperTrend regime boundary.
• Ehlers Detrended Synthetic Price (DSP) (entry) — Identifies cycle turning points within the larger regime by removing the trend component, signaling entry when the cycle aligns with the trend.
• Volume Price Confirmation Indicator (VPCI) (exit) — Exits trades when the relationship between price move and volume flow diverges, indicating trend exhaustion or lack of institutional confirmation.
• Average True Range (ATR) (risk) — Standardizes risk and stop-loss distance based on realized market volatility.

Known failure conditions

• The strategy fails in 'choppy' sideways markets where Ehlers DSP produces frequent zero-line crosses without trend follow-through.
• KNN classification accuracy drops significantly if the market undergoes a structural regime shift (e.g., transition from low-vol to high-vol volatility regimes).
• Failure of the VPCI to confirm price action in low-liquidity environments leading to premature exits.

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.