ArtificialIntelligence
This EA uses a linear perceptron model with four weights applied to Accelerator Oscillator (AC) indicator values at shifts 0, 7, 14, and 21 bars to generate buy/sell signals. When a signal opposes an existing profitable position, it performs a position reversal with increased volume; otherwise it trails the stop loss to breakeven plus spread. All positions require a stop loss and there is no take profit.
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 strategy is based on a linear perceptron that multiplies four AC indicator values at different bar shifts by optimizable weights and sums them; a positive output signals a buy and a negative output signals a sell. Entry conditions require the perceptron signal to trigger and the calculated stop loss to meet the broker's minimum stop level distance. Exit conditions rely primarily on stop loss, but when a position is profitable by more than twice the stop loss distance plus spread, the EA either reverses the position with increased volume on an opposing signal or trails the stop to breakeven if no opposing signal exists. Position sizing adds the new lot size to the existing position volume during reversals, which effectively increases exposure. Money management uses only fixed lot sizing with no dynamic adjustment based on equity or risk percentage. The strategy entirely lacks a take profit mechanism, depending solely on stop loss and breakeen trailing to manage the risk-reward ratio.
Strengths
- The perceptron model applies weighted combinations to AC indicator values, offering more flexibility than single-indicator signals
- Includes a breakeven stop loss trailing mechanism that locks in profit once the position moves sufficiently in favor
- Stop loss is mandatory, ensuring every trade has a risk exit in place
- Position reversal with increased volume can amplify gains when the market genuinely reverses direction
Weaknesses
- Position reversal increases exposure by adding volume, which can lead to rapid losses on consecutive false signals
- Completely lacks a take profit mechanism, meaning profitable positions can only exit via breakeen trailing or reversal, potentially giving back significant gains
- Perceptron weights require optimization but have no adaptive mechanism, so they may become ineffective after market regime changes
- Fixed lot sizing with no money management means risk cannot be dynamically adjusted based on account size
Possible improvements
- Add dynamic position sizing that adjusts lot size based on account equity and a risk percentage parameter
- Implement a take profit or trailing take profit mechanism to prevent significant drawdowns on winning positions
- Introduce an adaptive optimization mechanism for perceptron weights so they can adjust to changing market conditions
Risk assessment
Overall risk: Caution
- The reversal with added volume doubles risk per trade, and consecutive reversals can compound losses rapidly
- No take profit means relying on breakeen trailing, but sharp price reversals may give back profits before the stop can be moved
- High risk of perceptron weight overfitting, as historically optimized parameters may fail in live markets
Evaluation scores
Parameters
| Parameter | Default | Description |
|---|---|---|
Lots | 0.1 | Fixed trade lot size |
StopLoss | 850 | Stop loss in points |
Shift | 1 | Bar shift for indicator check: 0=current forming bar, 1=last formed bar |
x1 | 135 | Perceptron weight 1, range 0 to 200 |
x2 | 127 | Perceptron weight 2, range 0 to 200 |
x3 | 16 | Perceptron weight 3, range 0 to 200 |
x4 | 93 | Perceptron weight 4, range 0 to 200 |
Similar Machine Learning EAs
Backtests are historical simulations and do not guarantee future results. Not financial advice.