Exp_ColorXPWMA_Digit_NN3_MMRec
This EA uses a neural network (NN3) combined with the ColorXPWMA_Digit indicator to generate trading signals, with money management recommendations (MMRec). It employs a three-layer neural network for signal classification and applies position sizing based on configurable money management rules.
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: Elevated
- Increases the position size after losses (martingale)
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 leverages the ColorXPWMA_Digit indicator as feature input to a three-layer neural network (NN3) for signal classification and prediction. Entry conditions are based on neural network output signals, opening positions when the network identifies a trend direction. Exit conditions include stop loss, take profit, and position closing on reverse signals. Position sizing employs the MMRec money management module, dynamically adjusting lot size based on account balance and risk parameters. The strategy combines technical indicators with machine learning methods, attempting to improve signal quality through the neural network's nonlinear fitting capability. However, the neural network's training and generalization ability heavily depends on historical data quality, carrying overfitting risk.
Strengths
- Uses neural network for nonlinear signal classification, theoretically capturing complex patterns that traditional indicators miss
- ColorXPWMA_Digit indicator integrates multiple weighted moving averages, providing rich feature inputs
- Built-in MMRec money management module supports dynamic position sizing, aiding risk control
- Three-layer neural network architecture provides hierarchical feature extraction, improving model expressiveness
Weaknesses
- Neural network is highly prone to overfitting historical data, live performance may significantly lag backtesting results
- Model training and parameter tuning process is opaque, making it difficult for users to understand and verify strategy logic
- Lacks out-of-sample validation mechanism, unable to ensure model generalization ability
- Poor adaptability to market regime changes; statically trained neural network may fail when market structure shifts
- ColorXPWMA_Digit's digit quantization may lose important continuity information from the original signal
Possible improvements
- Add out-of-sample validation and cross-validation mechanisms to prevent overfitting and evaluate true generalization ability
- Introduce online learning or periodic retraining to allow the neural network to adapt to market regime changes
- Enhance risk control module with maximum drawdown limits, consecutive loss protection, and correlation filtering
Risk assessment
Overall risk: Caution
- High neural network overfitting risk; backtesting performance may not reflect live results
- No consecutive loss protection; may generate significant losses during model failure periods
- MMRec money management may calculate unreasonable position sizes under extreme market conditions
Evaluation scores
Parameters
| Parameter | Default | Description |
|---|---|---|
LotSize | 0.1 | Fixed lot size, used when MMRec is disabled |
StopLoss | 500 | Stop loss in points |
TakeProfit | 1000 | Take profit in points |
NN_Layer1 | varies | Number of neurons in neural network layer 1 |
NN_Layer2 | varies | Number of neurons in neural network layer 2 |
NN_Layer3 | varies | Number of neurons in neural network layer 3 |
MMRec_RiskPercent | 2.0 | Money management risk percentage |
XPWMA_Period | varies | ColorXPWMA indicator period parameter |
MagicNumber | varies | EA magic number |
Timeframe | 0 | TII calculation timeframe, 0 for current period |
Similar Machine Learning EAs
Backtests are historical simulations and do not guarantee future results. Not financial advice.