Articles on the MQL5 programming and use of trading robots

A multi-task learning framework based on ResNeXt optimizes the analysis of financial data, taking into account its high dimensionality, nonlinearity, and time dependencies. The use of group convolution and specialized heads allows the model to effectively extract key features from the input data.

We continue our acquaintance with the TEMPO method. In this article we will evaluate the actual effectiveness of the proposed approaches on real historical data.

In this article, we upgrade the MQL5 Multi-Timeframe Scanner Dashboard with movable and toggle features. We enable dragging the dashboard and a minimize/maximize option for better screen use. We implement and test these enhancements for improved trading flexibility.

The DeMarker Oscillator and the Envelopes' indicator are momentum and support/ resistance tools that can be paired when developing an Expert Advisor. We continue from our last article that introduced these pair of indicators by adding machine learning to the mix. We are using a recurrent neural network that uses the white-noise kernel to process vectorized signals from these two indicators. This is done in a custom signal class file that works with the MQL5 wizard to assemble an Expert Advisor.

In this session, we will build a sophisticated, multi-signal Expert Advisor using the MQL5 Standard Library. This approach allows us to seamlessly blend built-in signals with our own custom logic, demonstrating how to construct a powerful and flexible trading algorithm. For more, click to read further.

We continue to explore the innovative Chimera framework – a two-dimensional state-space model that uses neural network technologies to analyze multidimensional time series. This method provides high forecasting accuracy with low computational cost.

We have already made some progress in developing a multi-currency EA with several strategies working in parallel. Considering the accumulated experience, let's review the architecture of our solution and try to improve it before we go too far ahead.

Generating new indicators from existing ones offers a powerful way to enhance trading analysis. By defining a mathematical function that integrates the outputs of existing indicators, traders can create hybrid indicators that consolidate multiple signals into a single, efficient tool. This article introduces a new indicator built from three oscillators using a modified version of the Pearson correlation function, which we call the Pseudo Pearson Correlation (PPC). The PPC indicator aims to quantify the dynamic relationship between oscillators and apply it within a practical trading strategy.

In this article, we create buttons for currency pair filters, importance levels, time filters, and a cancel option to improve dashboard control. These buttons are programmed to respond dynamically to user actions, allowing seamless interaction. We also automate their behavior to reflect real-time changes on the dashboard. This enhances the overall functionality, mobility, and responsiveness of the panel.

With the rapid development of artificial intelligence today, language models (LLMs) are an important part of artificial intelligence, so we should think about how to integrate powerful LLMs into our algorithmic trading. For most people, it is difficult to fine-tune these powerful models according to their needs, deploy them locally, and then apply them to algorithmic trading. This series of articles will take a step-by-step approach to achieve this goal.

The last two articles were devoted to the Decision Transformer method, which models action sequences in the context of an autoregressive model of desired rewards. In this article, we will look at another optimization algorithm for this method.

Since the first articles devoted to reinforcement learning, we have in one way or another touched upon 2 problems: exploring the environment and determining the reward function. Recent articles have been devoted to the problem of exploration in offline learning. In this article, I would like to introduce you to an algorithm whose authors completely eliminated the reward function.

We continue the discussion about the use of piecewise linear representation of time series, which was started in the previous article. Today we will see how to combine this method with other approaches to time series analysis to improve the price trend prediction quality.

We continue studying the environment in reinforcement learning models. And in this article we will look at another algorithm – Go-Explore, which allows you to effectively explore the environment at the model training stage.

In financial markets, the laws of retracement remain among the most undeniable forces. It is a rule of thumb that price will always retrace—whether in large moves or even within the smallest tick patterns, which often appear as a zigzag. However, the retracement pattern itself is never fixed; it remains uncertain and subject to anticipation. This uncertainty explains why traders rely on multiple Fibonacci levels, each carrying a certain probability of influence. In this discussion, we introduce a refined strategy that applies Fibonacci techniques to address the challenges of trading shortly after major economic event announcements. By combining retracement principles with event-driven market behavior, we aim to uncover more reliable entry and exit opportunities. Join to explore the full discussion and see how Fibonacci can be adapted to post-event trading.

Understanding agent behavior is important in many different areas, but most methods focus on just one of the tasks (understanding, noise removal, or prediction), which reduces their effectiveness in real-world scenarios. In this article, we will get acquainted with a model that can adapt to solving various problems.

I invite you to explore the MacroHFT framework, which applies context-aware reinforcement learning and memory to improve high-frequency cryptocurrency trading decisions using macroeconomic data and adaptive agents.

In this article, we implement a module similar to requests offered in Python to make it easier to send and receive web requests in MetaTrader 5 using MQL5.

Linear Kernels are the simplest matrix of its kind used in machine learning for linear regression and support vector machines. The Matérn kernel on the other hand is a more versatile version of the Radial Basis Function we looked at in an earlier article, and it is adept at mapping functions that are not as smooth as the RBF would assume. We build a custom signal class that utilizes both kernels in forecasting long and short conditions.

In this article, we shift focus toward integrating news-driven order execution logic—enabling the EA to act, not just inform. Join us as we explore how to implement automated trade execution in MQL5 and extend the News Headline EA into a fully responsive trading system. Expert Advisors offer significant advantages for algorithmic developers thanks to the wide range of features they support. So far, we’ve focused on building a news and calendar events presentation tool, complete with integrated AI insights lanes and technical indicator insights.

Factorization is a mathematical process used to gain insights into the attributes of data. When we apply factorization to large sets of market data — organized in rows and columns — we can uncover patterns and characteristics of the market. Factorization is a powerful tool, and this article will show how you can use it within the MetaTrader 5 terminal, through the MQL5 API, to gain more profound insights into your market data.

The AI breakthroughs dominating headlines, from ChatGPT to self-driving cars, aren’t built from isolated models but through cumulative knowledge transferred from various models or common fields. Now, this same "learn once, apply everywhere" approach can be applied to help us transform our AI models in algorithmic trading. In this article, we are going to learn how we can leverage the information gained across various instruments to help in improving predictions on others using transfer learning.

In this article, we will have a look at yet another reinforcement learning approach. It is called goal-conditioned reinforcement learning (GCRL). In this approach, an agent is trained to achieve different goals in specific scenarios.

The number of strategies that can be integrated into an Expert Advisor is virtually limitless. However, each additional strategy increases the complexity of the algorithm. By incorporating multiple strategies, an Expert Advisor can better adapt to varying market conditions, potentially enhancing its profitability. Today, we will explore how to implement MQL5 for one of the prominent strategies developed by Richard Donchian, as we continue to enhance the functionality of our Trend Constraint Expert.

In this article, we will continue our articles about Design Patterns after learning how much this topic is more important for us as developers to develop extendable, reliable applications not only by the MQL5 programming language but others as well. We will learn about another type of Design Patterns which is the structural one to learn how to design systems by using what we have as classes to form larger structures.

Lightweight time series forecasting models achieve high performance using a minimum number of parameters. This, in turn, reduces the consumption of computing resources and speeds up decision-making. Despite being lightweight, such models achieve forecast quality comparable to more complex ones.

This tool is a Correlation Dashboard that calculates and displays real-time correlation coefficients across multiple currency pairs. By visualizing how pairs move in relation to one another, it adds valuable context to your price-action analysis and helps you anticipate inter-market dynamics. Read on to explore its features and applications.

In this article, I propose to look at the issue of building a trading strategy from a different angle. We will not predict future price movements, but will try to build a trading system based on the analysis of historical data.

In this series of articles, we revisit classical strategies to see if we can improve the strategy using AI. In today's article, we will examine a popular strategy of multiple symbol analysis using a basket of correlated securities, we will focus on the exotic USDZAR currency pair.

The Angle of Attack is an often-quoted metric whose steepness is understood to strongly correlate with the strength of a prevailing trend. We look at how it is commonly used and understood and examine if there are changes that could be introduced in how it's measured for the benefit of a trade system that puts it in use.

In this article, we will enhance the responsiveness of the Admin Panel that we previously created. Additionally, we will explore the significance of quick messaging in the context of trading signals.