Skip to content
All library documents

Using ONNX Machine-Learning Models in an Automated EURUSD Trading Bot

Article MQL5 code base
Read the original

Summary

This document describes an automated trading bot that connects machine-learning models trained in Python and converted to ONNX format. It presents configurable controls for risk-based or fixed lot sizing, order limits, stop loss, and take profit, and notes that users can add filters or optimize exit distances across timeframes. A separate set of examples applies k-means clustering to trade matching. The described models use EURUSD hourly data, with training from 2010 to 2020 and a forward period from 2020 to 2024.

The page is an archive and integration guide rather than a strategy evaluation. It does not report returns, drawdowns, benchmark comparisons, or details about features, labels, costs, or model-selection procedures. It says models may differ with training hyperparameters, and suggests they can be used on other timeframes, but gives no evidence that performance transfers across intervals or market conditions. The listed risk and exit parameters are configuration examples, not validated recommendations.

Key ideas

  • The bot runs machine-learning models trained in Python after conversion to ONNX format.
  • Users can configure order sizing, order limits, stop loss, and take profit, and can add filters.
  • The clustering examples use k-means and models trained on EURUSD hourly data.
  • The stated training period is 2010–2020, with a forward period from 2020–2024.
  • The document provides no performance evidence or support for transferring results to other timeframes.

Tags

ForexMachine learningExecutionRisk management

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.