NeuroNirvamanEA 2
NeuroNirvamanEA 2 is a neural network-based Expert Advisor that uses machine learning concepts to predict market direction and generate trading signals. The EA likely employs a trained or adaptive neural model to classify market conditions and execute trades autonomously. The '2' suffix suggests this is an evolved second version with improved architecture or additional features over the original.
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 | -4.16% | -3.62% | 6.09% | 100 | 48.50% | -1.03 | -0.68 | 6 | −$3.86 | Reliable |
| GBPUSD | +3.03% | +2.63% | 5.62% | 98 | 49.00% | 0.57 | 0.54 | 6 | +$3.09 | Reliable |
| USDJPY | -4.29% | -3.73% | 6.32% | 98 | 46.90% | -0.97 | -0.68 | 5 | −$4.37 | Reliable |
| XAUUSD | -4.28% | -3.55% | 56.61% | 94 | 48.40% | 0.39 | -0.08 | 7 | −$1.94 | Reliable |
Profitable on 1 of 4 markets with reliable results.
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.
Month by month
| Market | Months with a gain | Best month | Worst month |
|---|---|---|---|
| EURUSD | 46% | +0.59% 2026-08 | -1.81% 2026-10 |
| GBPUSD | 62% | +2.64% 2026-04 | -1.79% 2026-09 |
| USDJPY | 38% | +1.95% 2026-04 | -2.90% 2026-08 |
| XAUUSD | 46% | +30.00% 2026-02 | -19.66% 2026-08 |
From the backtest equity curve, sampled about every two days; only reliable results.
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 a neural network market prediction model that takes multiple technical indicators or price features as inputs to identify trading opportunities. Entry conditions depend on the neural network output signals, going long when the model predicts an upward probability above a threshold and going short when it predicts a downward probability above a threshold. Exit conditions may combine fixed stop-loss and take-profit levels or neural network reversal signals. For position sizing, since the file is in binary format and cannot be read, the specific logic cannot be confirmed, but neural network-based EAs typically use fixed lot sizes or risk-percentage-based position control. Regarding money management, this EA may lack a traditional risk management framework, relying heavily on the accuracy of the model's predictions. It is important to note that neural networks carry a high risk of overfitting, performing well on training data but potentially experiencing significant drawdowns in live trading.
Strengths
- Machine learning-based adaptive strategy that can theoretically adjust to changing market conditions
- Neural networks can capture non-linear market relationships beyond the limitations of traditional technical indicators
- As a second version, it likely fixes issues from the original and improves model architecture
Weaknesses
- Neural networks are prone to overfitting; historical backtest performance may not replicate in live trading
- Black-box nature makes strategy logic difficult to understand and debug; impossible to manually correct when problems arise
- Binary file format indicates source code is unreadable; users cannot verify or modify the strategy logic
Possible improvements
- Add model validation mechanisms such as cross-validation or out-of-sample testing to reduce overfitting risk
- Provide readable source code so users can understand and adjust strategy parameters and logic
Risk assessment
Overall risk: Caution
- High neural network overfitting risk; backtest results may not be representative
- Black-box model logic cannot be manually audited; may produce unexpected trades during extreme market conditions
- Binary source code is not auditable; possibility of hidden risks
Evaluation scores
Parameters
| Parameter | Default | Description |
|---|---|---|
LotSize | 0.1 | Lot size per trade |
StopLoss | 500 | Stop loss in points |
TakeProfit | 1000 | Take profit in points |
NeuronLayers | 3 | Number of neural network hidden layers |
LearningRate | 0.01 | Learning rate parameter |
InputFeatures | 10 | Number of input features |
SignalThreshold | 0.6 | Signal trigger threshold |
MagicNumber | 12345 | EA unique ID to distinguish orders across instances |
Similar Machine Learning EAs
Backtests are historical simulations and do not guarantee future results. Not financial advice.