Logistic-Cyclic Pullback Navigator
Family: hybrid · Regime: trending · Complexity: high · Asset classes: Crypto (ATOMUSDT), Gold (XAUUSD) · Timeframes: 15m, 1H
Thesis
The market exhibits cyclic fluctuations within broader trends. By using a logistic regression model to predict directional probability and an Ehlers Center of Gravity oscillator to time the end of mean-reverting pullbacks, we can enter trends with higher precision and lower lag than standard MA-crossover systems. This hypothesis assumes the market's local 'balance point' (CG) is a lead indicator for trend resumption.
Components
- XAU Trend Volatility Filter (XAU_TVF) (regime) — Defines the trend-volatility regime to ensure entries only occur when price movement is supported by sufficient momentum and 'volatility pressure'.
- Linear Regression (LINREG) (direction) — Determines the primary trade direction by fitting a least-squares line to capture the underlying price slope.
- Stochastic Oscillator (ta.stoch) (entry) — Identifies short-term mean-reversion pullbacks (oversold/overbought) within the established trend.
- ATR Heiken Ashi (exit) — Uses smoothed synthetic price data to define a volatility-adjusted exit if the trend loses its characteristic 'smooth' movement.
- ATOM Coefficient Indicator (logit) (risk) — Provides a logistic-regression-based probabilistic filter and defines the structural ATR-based risk parameters.
- Ehlers Center of Gravity (CG) (confirmation) — Provides zero-lag cyclic confirmation that the local pullback is reverting back to the mean.
Known failure conditions
- ATOM Coefficient P-value remains between 0.45 and 0.55 for more than 40 consecutive 15m bars (regime death).
- XAU_TVF TrendScore consistently disagrees with LINREG Slope for 5+ trades.
- The strategy achieves a Drawdown > 2x the predicted logistic model error margin.
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).