ArbSint
ArbSint is a statistical arbitrage EA that exploits price divergence between correlated or cointegrated instruments. It opens opposing positions when the spread deviates beyond a threshold and closes them when the spread reverts to the mean. The strategy is inherently market-neutral, aiming to profit from relative value convergence rather than directional movement.
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
- Has no stop loss or trailing stop
On its own this is not a typical blow-up pattern, 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 concept of ArbSint is statistical arbitrage, based on the spread divergence and mean-reversion properties between two or more correlated financial instruments. Entry conditions trigger when the spread (or synthetic price difference) between two correlated symbols deviates beyond a predefined threshold from its statistical mean, simultaneously opening opposing positions—going long on the undervalued instrument and short on the overvalued one. Exit conditions are met when the spread reverts to its mean or reaches a specified target profit, at which point both positions are closed simultaneously to capture the arbitrage profit. Position sizing typically employs equal-value pairing to ensure the market exposure on both legs is essentially hedged. Money management adjusts lot sizes based on the degree of spread deviation and account risk limits, though statistical arbitrage inherently carries relatively controlled risk due to the always-hedged long-short positioning. A key risk to monitor is the potential breakdown of the cointegration relationship, which could cause the two instruments' prices to diverge persistently without reverting, resulting in losses on both legs.
Strengths
- Market-neutral strategy immune to directional market risk, reducing exposure to trend bias
- Statistical arbitrage grounded in quantifiable mean-reversion principles with clear mathematical justification
- Hedged position structure limits maximum loss exposure, keeping risk relatively contained
- Capable of generating profits in both ranging and trending markets, offering strong adaptability
- Exploits structural divergence between correlated instruments, capturing opportunities invisible to traditional technical analysis
Weaknesses
- Cointegration relationship may break down during structural market shifts, causing losses on both legs simultaneously
- Statistical parameters (mean, standard deviation) rely on historical data and may fail in non-stationary markets
- Requires both instruments to have sufficient liquidity and low spreads, as transaction costs can erode arbitrage profits
- Spread reversion timing is uncertain, potentially tying up margin in prolonged positions
- Over-reliance on historical correlation assumptions; during black swan events correlations may converge toward 1, rendering hedges ineffective
Possible improvements
- Add dynamic cointegration testing (e.g., ADF test) to automatically pause trading when the cointegration relationship breaks down
- Implement adaptive parameter adjustment to dynamically calibrate deviation thresholds and position sizes based on prevailing market volatility
Risk assessment
Overall risk: Medium
- Cointegration breakdown risk: spread between two instruments may persistently diverge without reverting, causing hedged positions to lose on both legs
- Holding period risk: uncertain spread reversion timing may tie up significant margin and increase overnight exposure
Evaluation scores
Parameters
| Parameter | Default | Description |
|---|---|---|
SpreadThreshold | 2.0 | Spread deviation threshold for opening positions |
TakeProfit | 50 | Take profit in points |
StopLoss | 200 | Stop loss in points for cointegration break protection |
LotSize | 0.1 | Lot size per leg |
LookbackPeriod | 100 | Lookback period for mean and standard deviation |
Symbol1 | EURUSD | Pair symbol 1 |
Symbol2 | GBPUSD | Pair symbol 2 |
MagicNumber | 12345 | EA order magic number |
Similar Statistical Arbitrage EAs
Backtests are historical simulations and do not guarantee future results. Not financial advice.