Articles on MetaTrader 5 integration using MQL5

Historical data is far from “trash”—it’s the foundation of any robust market analysis. In this article, we’ll take you step‑by‑step from collecting that history to using it to train a predictive model, and finally deploying that model for live price forecasts. Read on to learn how!

The multilayer perceptron is an evolution of the simple perceptron which can solve non-linear separable problems. Together with the backpropagation algorithm, this neural network can be effectively trained. In Part 3 of the Multilayer Perceptron and Backpropagation series, we'll see how to integrate this technique into the Strategy Tester. This integration will allow the use of complex data analysis aimed at making better decisions to optimize your trading strategies. In this article, we will discuss the advantages and problems of this technique.

We are introducing MQL5 Algo Forge — a dedicated portal for algorithmic trading developers. It combines the power of Git with an intuitive interface for managing and organizing projects within the MQL5 ecosystem. Here, you can follow interesting authors, form teams, and collaborate on algorithmic trading projects.

In this article, we upgrade the ChatGPT-integrated program in MQL5 to a scrollable single chat-oriented UI, enhancing conversation history display with timestamps and dynamic scrolling. The system builds on JSON parsing to manage multi-turn messages, supporting customizable scrollbar modes and hover effects for improved user interaction.

In this series of articles, we have already mentioned Transfer Learning more than once. However, this was only mentioning. in this article, I suggest filling this gap and taking a closer look at Transfer Learning.

We continue the series of articles on developing a trading robot in Python and MQL5. Today we will solve the problem of selecting and training a model, testing it, implementing cross-validation, grid search, as well as the problem of model ensemble.

In this article, we integrate interactive inline buttons into an MQL5 Expert Advisor, allowing real-time control via Telegram. Each button press triggers specific actions and sends responses back to the user. We also modularize functions for handling Telegram messages and callback queries efficiently.

This article reports the first attempts in the development of a native MQTT client for MQL5. MQTT is a Client Server publish/subscribe messaging transport protocol. It is lightweight, open, simple, and designed to be easy to implement. These characteristics make it ideal for use in many situations.

This article describes the implementation of a regression model based on a decision tree. The model should predict prices of financial assets. We have already prepared the data, trained and evaluated the model, as well as adjusted and optimized it. However, it is important to note that this model is intended for study purposes only and should not be used in real trading.

This article follows up ‘Part-74’, where we examined the pairing of Ichimoku and the ADX under a Supervised Learning framework, by moving our focus to Reinforcement Learning. Ichimoku and ADX form a complementary combination of support/resistance mapping and trend strength spotting. In this installment, we indulge in how the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm can be used with this indicator set. As with earlier parts of the series, the implementation is carried out in a custom signal class designed for integration with the MQL5 Wizard, which facilitates seamless Expert Advisor assembly.

25 to 30% of all crashlogs received from users appear due to errors occurring when functions imported from custom dlls are executed.

Gamma and Delta measure how an option’s value reacts to changes in the underlying asset’s price. Delta represents the rate of change of the option’s price relative to the underlying, while Gamma measures how Delta itself changes as price moves. Together, they describe an option’s directional sensitivity and convexity—critical for dynamic hedging and volatility-based trading strategies.

Continued from the part 1 in the series, now we proceed to implement as a simple DLL then test with MetaTrader 5. This will prepare us well before developing a full-fledge OpenCL as DLL support in the following part to come.

Bulit-in OpenCL support in MetaTrader 5 still has a major problem especially the one about device selection error 5114 resulting from unable to create an OpenCL context using CL_USE_GPU_ONLY, or CL_USE_GPU_DOUBLE_ONLY although it properly detects GPU. It works fine with directly using of ordinal number of GPU device we found in Journal tab, but that's still considered a bug, and users should not hard-code a device. We will solve it by recreating an OpenCL support as DLL with C++ on Linux. Along the journey, we will get to know OpenCL from concept to best practices in its API usage just enough for us to put into great use later when we deal with DLL implementation in C++ and consume it with MQL5.

Bollinger Bands are a very common Envelope Indicator used by a lot of traders to manually place and close trades. We examine this indicator by considering as many of the different possible signals it does generate, and see how they could be put to use in a wizard assembled Expert Advisor.