Discussing the article: "Certified Robustness Radius: Knowing How Much Noise Your ONNX Trading Model Can Survive"

[MetaQuotes]

Check out the new article: Certified Robustness Radius: Knowing How Much Noise Your ONNX Trading Model Can Survive.

We introduce a certified-radius gate for ONNX signals implemented natively in MQL5. The system estimates per-prediction robustness via randomized smoothing and a one-sided Clopper–Pearson bound, then applies the radius to trade admission, lot scaling, and monitoring. This provides an actionable confidence margin that reflects input noise tolerance rather than softmax magnitude.

Every ONNX-driven trading system I've built eventually runs into the same silent problem: the model outputs a class, you trust the class, and you never ask how close it was to being a different class entirely. A softmax score of 0.51 for "long" gets treated the same as 0.98 — both open the same position at the same size. But one signal is a coin flip from flipping to "short," and the other is a genuinely confident read. Softmax confidence isn't calibrated as a distance to the decision boundary, so it doesn't reliably tell you which situation you're in.

This article builds a native MQL5 system that answers a different question: not "what did the model predict," but "how much could the input change before the prediction would flip." That's a certified robustness radius, from a technique originally built to defend image classifiers against adversarial attacks — randomized smoothing — repurposed here for a more mundane threat: noisy live feeds, tick jitter, spread spikes, and stale-bar artifacts that can flip a fragile prediction.

By the end you'll have a working EA that runs every trade decision through certification before acting, sizes positions by how robust the signal is, and logs a rolling radius history so you can review a model's confidence margins over time.

Author: Adedayo David Gbadebo