Lorentzian PVT Volume-ML Hybrid
Family: hybrid · Regime: trending · Complexity: high · Asset classes: EQUITIES, CRYPTO, FOREX · Timeframes: 1H, 4H, Daily
Thesis
Market edges exist when machine-learning-derived historical similarities (Lorentzian) align with cumulative volume flow (PVT). By entering during oversold pullbacks (RSI) that show active accumulation (A/D) within a defined structural zone (Probable High/Low), we exploit the behavioral tendency of trends to persist after short-term mean-reversion events.
Components
- Price Volume Trend (PVT) (regime) — Acts as the primary regime filter to ensure price movement is supported by volume flow momentum.
- Lorentzian Classification (direction) — Uses non-Euclidean distance to classify current market structure based on historical similarities in RSI/CCI space.
- AI - RSI Strategy (entry) — Provides the tactical entry trigger by identifying oversold/overbought conditions within the context of a long-term SMA filter.
- ATR Heiken Ashi (exit) — Utilizes smoothed price data to determine trend exhaustion for exits, reducing noise compared to standard price action.
- Average True Range (ATR) (risk) — Standard volatility measurement for calculating dynamic stop-loss distances and volatility-adjusted position sizing.
- Accumulation/Distribution (A/D) (confirmation) — Confirms entry signals by ensuring money flow is aligned with the price direction (absence of divergence).
- Probable High Low (volatility_filter) — Provides hardcoded structural bounds to prevent entering trades near historical supply/demand extremes.
Known failure conditions
- The hardcoded Probable High/Low levels are breached and stay outside for extended periods, rendering the filter obsolete.
- Lorentzian KNN classification shows a win-rate drop below 45% in backtests, suggesting feature drift.
- Volume (PVT/AD) diverges consistently from price, indicating a decoupling of liquidity and momentum.
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.