Articles on trading system automation in MQL5

Volatility tends to peak around high-impact news events, creating significant breakout opportunities. In this article, we will outline the implementation process of a calendar-based breakout strategy. We'll cover everything from creating a class to interpret and store calendar data, developing realistic backtests using this data, and finally, implementing execution code for live trading.

We continue to explore reinforcement learning methods. In this article, I will focus on a slightly different algorithm that considers the Agent’s policy in the paradigm of constructing a sequence of actions.

The article implements a fast strategy tester for machine learning models using Numba. It is 50 times faster than the pure Python strategy tester. The author recommends using this library to speed up mathematical calculations, especially the ones involving loops.

The article presents a simple and accessible way to use a neural network in a trading EA that does not require deep knowledge of machine learning. The method eliminates the target function normalization, as well as overcomes "weight explosion" and "network stall" issues offering intuitive training and visual control of the results.

Do you know what really drives a currency pair’s direction? It’s the strength of each individual currency. In this article, we’ll measure a currency’s strength by looping through every pair it appears in. That insight lets us predict how those pairs may move based on their relative strengths. Read on to learn more.

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.

We continue to discuss algorithms for training trajectory prediction models. In this article, we will get acquainted with a method called "AutoBots".

The ADX is another relatively popular technical indicator used by some traders to gauge the strength of a prevalent trend. Acting as a combination of two other indicators, it presents as an oscillator whose patterns we explore in this article with the help of MQL5 wizard assembly and its support classes.

The flow of the market is determined by the forces between bulls and bears. There are specific levels that the market respects due to the forces acting on them. Fibonacci and VWAP levels are especially powerful in influencing market behavior. Join me in this article as we explore a strategy based on VWAP and Fibonacci levels for signal generation.

This article is aimed at beginners and pro-MQL5 developers. It provides a piece of code to define and constrain signal-generating indicators to trends in higher timeframes. In this way, traders can enhance their strategies by incorporating a broader market perspective, leading to potentially more robust and reliable trading signals.

Learn how to develop and implement a comprehensive pending orders EX5 library in your MQL5 code or projects. This article will show you how to create an extensive pending orders management EX5 library and guide you through importing and implementing it by building a trading panel or graphical user interface (GUI). The expert advisor orders panel will allow users to open, monitor, and delete pending orders associated with a specified magic number directly from the graphical interface on the chart window.

Let's move on to a more complete order system directly on the chart. In this article, I will show a way to fix the order system, or rather, to make it more intuitive.

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.

Currently, our EA uses the database to obtain initialization strings for single instances of trading strategies. However, the database is quite large and contains a lot of information that is not needed for the actual EA operation. Let's try to ensure the EA's functionality without a mandatory connection to the database.

Trends are an important part of many trading strategies. In this article, we will look at some of the tools used to identify trends and their characteristics. Understanding and correctly interpreting trends can significantly improve trading efficiency and minimize risks.

We continue to study unsupervised learning algorithms. Some readers might have questions regarding the relevance of recent publications to the topic of neural networks. In this new article, we get back to studying neural networks.

We have already talked more than once about the importance of correctly selecting the reward function, which we use to stimulate the desired behavior of the Agent by adding rewards or penalties for individual actions. But the question remains open about the decryption of our signals by the Agent. In this article, we will talk about reward decomposition in terms of transmitting individual signals to the trained Agent.

Determining market direction can be straightforward, but knowing when to enter can be challenging. As part of the series titled "Price Action Analysis Toolkit Development", I am excited to introduce another tool that provides entry points, take profit levels, and stop loss placements. To achieve this, we have utilized the MQL5 programming language. Let’s delve into each step in this article.

We have already implemented the first stage of the automated optimization. We perform optimization for different symbols and timeframes according to several criteria and store information about the results of each pass in the database. Now we are going to select the best groups of parameter sets from those found at the first stage.

In an attempt to obtain the most accurate forecasts, researchers often complicate forecasting models. Which in turn leads to increased model training and maintenance costs. Is such an increase always justified? This article introduces an algorithm that uses the simplicity and speed of linear models and demonstrates results on par with the best models with a more complex architecture.

We will analyze the question of what quantitative analysis is and how it is used by major players. We will create one of the quantitative analysis algorithms in the MQL5 language.

In the previous article, we introduced the multi-agent adaptive framework MASAAT, which uses an ensemble of agents to perform cross-analysis of multimodal time series at different data scales. Today we will continue implementing the approaches of this framework in MQL5 and bring this work to a logical conclusion.

Discover how to fix a critical flaw in financial machine learning that causes overfit models and poor live performance—label concurrency. When using the triple-barrier method, your training labels overlap in time, violating the core IID assumption of most ML algorithms. This article provides a hands-on solution through sample weighting. You will learn how to quantify temporal overlap between trading signals, calculate sample weights that reflect each observation's unique information, and implement these weights in scikit-learn to build more robust classifiers. Learning these essential techniques will make your trading models more robust, reliable and profitable.

Models are trained offline using data from a prepared training dataset. While providing certain advantages, its negative side is that information about the environment is greatly compressed to the size of the training dataset. Which, in turn, limits the possibilities of exploration. In this article, we will consider a method that enables the filling of a training dataset with the most diverse data possible.

We will make the order system more flexible. Here we will consider changes to the code that will make it more flexible, which will allow us to change position stop levels much faster.

The LSEAttention framework offers improvements to the Transformer architecture. It was designed specifically for long-term multivariate time series forecasting. The approaches proposed by the authors of the method can be applied to solve problems of entropy collapse and learning instability, which are often encountered with vanilla Transformer.