Adaptive SMA and EMA Trading with ONNX Predictions and Optimized Exits
Summary
This article describes an Expert Advisor that combines an ONNX price classifier with SMA and EMA trend filters. Predicted direction is used to trigger trades only when price also lies on the corresponding side of both moving averages. The system periodically adjusts moving-average periods and stop-loss and take-profit parameters, with ATR-based exit distances, trailing-stop options, and position management features.
The article outlines the EA’s components and presents backtest results as favorable on profit and risk management overall, while acknowledging high drawdowns and the need for further safeguards and optimization. The evidence is limited: the supplied text does not specify enough about the test period, market conditions, or validation method to judge robustness. It also contains conflicting instrument references, describing forex and EURUSD model resources while saying the EA targets AAPL. The strategy therefore serves mainly as an implementation example; its predictive edge and performance across instruments are not established.
Key ideas
- The EA combines an ONNX price-direction prediction with SMA and EMA trend confirmation.
- It periodically optimizes indicator periods and stop parameters, including ATR-based exit distances.
- Trailing-stop logic and position sizing features are included in the trading system.
- The article reports high drawdowns in backtesting despite positive-sounding overall results.
- Conflicting instrument references and limited test details make the reported performance difficult to assess.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.