Neural-Ashi Momentum Trail Strategy

Family: hybrid · Regime: trending · Complexity: medium · Asset classes: FX, Equities, Crypto · Timeframes: H1, H4, D1

Thesis

Market trends exhibit momentum 'ebbs and flows'; by combining a smoothed trend regime (Heikin-Ashi) with a non-linear momentum classifier (NNind) and a raw acceleration trigger (ROC), we can identify high-probability entries. The edge exists because the ML component captures non-linear price patterns while the volatility-based stop (TopTrend) protects against standard market variance better than fixed stops.

Components

• Heikin-Ashi Candles (regime) — Provides a smoothed price trend filter (regime) to ensure entries occur within established directional moves while ignoring minor counter-trend wicks.
• Neural Network Indicator (NNind) (direction) — Acts as an ML-filtered momentum filter (direction); it attempts to capture non-linear price patterns to confirm the quality of the trend.
• Rate of Change (ROC) (entry) — The raw momentum trigger; used to identify the specific acceleration point for entry.
• MACD (exit) — Serves as a trailing momentum exit to capture the meat of the move and exit before a full trend reversal.
• TopTrend (BBands Stop) (risk) — Provides a volatility-adjusted dynamic stop-loss and trailing mechanism that accounts for market expansion.

Known failure conditions

• Persistent regime of 'mean-reversion' where ROC crosses fail to lead to sustained momentum.
• Neural Network weights become permanently outdated due to structural market shifts (e.g., changes in central bank policy regimes).
• MACD signal line crosses frequently occur within the noise floor of the TopTrend stop.

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).