Exp_ColorX2MA_Digit_NN3_MMRec
This EA is a trend-following expert advisor that uses a double smoothed moving average (ColorX2MA) with digital filtering and a 3-layer neural network (NN3) for signal generation. It incorporates money management recommendations (MMRec) for dynamic position sizing based on account equity and risk parameters. The system enters trades on crossover signals confirmed by the neural network classifier and manages exits via trailing stops or opposite signals.
Open the interactive view (equity curve, symbol switch)Key facts
Backtest results (H1, about 1 year)
| Symbol | P&L | Annual | Max DD | Trades | Win rate | Sharpe | Recovery | Losing streak | Per trade | Status |
|---|---|---|---|---|---|---|---|---|---|---|
| EURUSD | 0.00% | 0.00% | 0.00% | 0 | — | — | — | — | — | Not convertible yet |
| GBPUSD | 0.00% | 0.00% | 0.00% | 0 | — | — | — | — | — | Not convertible yet |
| USDJPY | 0.00% | 0.00% | 0.00% | 0 | — | — | — | — | — | Not convertible yet |
| XAUUSD | 0.00% | 0.00% | 0.00% | 0 | — | — | — | — | — | Not convertible yet |
Why this EA never traded: no entry rule survived the conversion.
Converted from MQL5 to Python and run with the same rules for every EA. Positions use MT5 lot sizes (100,000 units per FX lot, 100 oz per gold lot) with 1:100 leverage, one order at a time, and a stop-out below 10% of the starting balance. Sharpe is computed from the equity curve. Results marked as unreliable are shown for completeness only.
Blow-up risk: No blow-up pattern found
None of the usual blow-up patterns were found in the code, and the account was not stopped out in our backtests. That is not a guarantee: any EA can lose money.
High: stopped out in our backtest, or martingale/grid sizing without a stop loss. Elevated: martingale or grid sizing with a stop loss, or several positions at once without a stop loss. What the label means and what we found →
Strategy analysis
The core strategy of this EA is based on crossover signals from the ColorX2MA double smoothed moving average to determine trend direction, going long when the fast line crosses above the slow line and short when it crosses below. The digital filtering (Digit) module preprocesses price data to reduce noise and improve signal quality. The three-layer neural network (NN3) serves as a signal confirmation layer, providing secondary verification of MA crossover signals to filter out low-quality false breakout signals. The money management recommendation (MMRec) module dynamically calculates position size for each trade based on account equity, risk ratio, and stop-loss distance, achieving risk-controlled capital management. Exit mechanisms include both trailing stops and opposite signal closing, ensuring timely exits when trends reverse. The overall strategy integrates traditional technical indicators with machine learning methods, attempting to strike a balance between the robustness of trend following and signal precision.
Strengths
- Integrates neural network with traditional technical indicators, dual signal confirmation reduces false signals
- Built-in money management recommendation module dynamically adjusts position size based on account equity for controlled risk
- Digital filtering preprocessing reduces price noise, improving signal quality and stability
Weaknesses
- Neural network implementation in MetaTrader 5 is typically a pre-trained feedforward model lacking online learning capability, unable to adapt to market regime changes
- Double smoothed MA is inherently a lagging indicator, prone to frequent false breakout signals in ranging markets leading to consecutive losses
- High strategy complexity with many parameters may lead to overfitting, and backtesting results may lack forward validity
Possible improvements
- Add a market regime identification module that automatically reduces position size or pauses trading in ranging markets, avoiding losses from trend strategies in non-trending environments
- Add periodic retraining mechanism for the neural network so the model can adapt to changes in current market characteristics
Risk assessment
Overall risk: Medium
- Trend following strategy may produce consecutive losses in ranging markets, lacking clear market state switching protection
- Pre-trained neural network model cannot adapt to sudden market structural changes and may fail during black swan events
Evaluation scores
Parameters
| Parameter | Default | Description |
|---|---|---|
ColorX2MA_Period1 | 14 | Fast line smoothing period |
ColorX2MA_Period2 | 28 | Slow line smoothing period |
ColorX2MA_Method | MODE_EMA | moving averagecalculation method |
Digit_Filter | true | Enable digital filter |
NN3_Layer1_Neurons | 32 | Neural network layer 1 neuron count |
NN3_Layer2_Neurons | 16 | Neural network layer 2 neuron count |
NN3_Layer3_Neurons | 8 | Neural network layer 3 neuron count |
MMRec_RiskPercent | 2.0 | Risk percentage per trade |
MMRec_MaxLot | 10.0 | Maximum allowed lot size |
StopLoss | 500 | Stop loss in points |
TakeProfit | 1000 | Take profit in points |
TrailingStop | 300 | Trailing stop distance in points from current price |
UseNN3Confirm | true | Enable neural network confirmation |
Similar Trend Following EAs
Backtests are historical simulations and do not guarantee future results. Not financial advice.