Articles on trading system automation in MQL5

Today, we explore another component of ALGLIB, leveraging its mathematical capabilities to develop a Polynomial Regression Channel indicator. By the end of this discussion, you will gain practical insights into indicator development using the MQL5 Standard Library, along with a fully functional, mathematically driven indicator source code.

The article presents the African Buffalo Optimization (ABO) algorithm, a metaheuristic approach developed in 2015 based on the unique behavior of these animals. The article describes in detail the stages of the algorithm implementation and its efficiency in finding solutions to complex problems, which makes it a valuable tool in the field of optimization.

In the first part of this article, we will dive into the world of chemical reactions and discover a new approach to optimization! Chemical reaction optimization (CRO) uses principles derived from the laws of thermodynamics to achieve efficient results. We will reveal the secrets of decomposition, synthesis and other chemical processes that became the basis of this innovative method.

This article describes the use of CSV files for backtesting portfolio weights updates in a mean-reversion-based strategy that uses statistical arbitrage through cointegrated stocks. It goes from feeding the database with the results of a Rolling Windows Eigenvector Comparison (RWEC) to comparing the backtest reports. In the meantime, the article details the role of each RWEC parameter and its impact in the overall backtest result, showing how the comparison of the relative drawdown can help us to further improve those parameters.

In this article, we explore the File Operations classes of the MQL5 Standard Library to build a robust reporting module that automatically generates Excel-ready CSV files. Along the way, we clearly distinguish between manually executed trades and algorithmically executed orders, laying the groundwork for reliable, auditable trade reporting.

Today we will look at why we need the iSpread feature. At the same time, we will understand how the system informs us about the remaining time of the bar when there is not a single tick available for it. The content presented here is intended solely for educational purposes. Under no circumstances should the application be viewed for any purpose other than to learn and master the concepts presented.

The article presents a step-by-step development of a multi-threaded trading robot with machine learning in Python and MetaTrader 5. The system architecture is considered – from data collection and creation of technical indicators to training XGBoost models with portfolio risk management. The implementation of data augmentation, feature clustering via Gaussian Mixture Models, and flow coordination for parallel trading of multiple currency pairs is described in detail.

Unlike what was done in the previous article, here we will test the selection option using an Expert Advisor. Although this is not a final solution yet, it will be enough for now. With the help of this article, you will be able to understand how to implement one of the possible solutions.

Support Vector Machines classify data based on predefined classes by exploring the effects of increasing its dimensionality. It is a supervised learning method that is fairly complex given its potential to deal with multi-dimensioned data. For this article we consider how it’s very basic implementation of 2-dimensioned data can be done more efficiently with Newton’s Polynomial when classifying price-action.

Automated trading systems often focus heavily on signal generation while neglecting the mechanisms required to protect capital during periods of stress. This article presents an Equity Governance Framework in MQL5 that monitors drawdown conditions, evaluates equity pressure, and dynamically controls trading activity through a state-driven risk management model. By combining drawdown analysis, cooldown logic, trade authorization, and execution restrictions, the framework demonstrates how trading discipline can be engineered directly into code using a modular and extensible architecture.

We continue exploring a multi-task learning framework based on ResNeXt, which is characterized by modularity, high computational efficiency, and the ability to identify stable patterns in data. Using a single encoder and specialized "heads" reduces the risk of model overfitting and improves the quality of forecasts.

Automated trading systems often focus heavily on signal generation while neglecting the mechanisms required to protect capital during periods of stress. This article presents an Equity Governance Framework in MQL5 that monitors drawdown conditions, evaluates equity pressure, and dynamically controls trading activity through a state-driven risk management model. By combining drawdown analysis, cooldown logic, trade authorization, and execution restrictions, the framework demonstrates how trading discipline can be engineered directly into code using a modular and extensible architecture.

The article discusses the practical implementation of the HiSSD framework in algorithmic trading tasks. It explains how the skill hierarchy and adaptive architecture can be used to build sustainable trading strategies.

In this article, we explore vector-based methods for drawing rounded rectangles and triangles in MQL5 using canvas, with supersampling for anti-aliased rendering. We implement scanline filling, geometric precomputations for arcs and tangents, and border drawing to create smooth, customizable shapes. This approach lays the groundwork for modern UI elements in future trading tools, supporting inputs for sizes, radii, borders, and opacities.

Temporal Difference is another algorithm in reinforcement learning that updates Q-Values basing on the difference between predicted and actual rewards during agent training. It specifically dwells on updating Q-Values without minding their state-action pairing. We therefore look to see how to apply this, as we have with previous articles, in a wizard assembled Expert Advisor.

The Parabolic Stop-and-Reversal (SAR) is an indicator for trend confirmation and trend termination points. Because it is a laggard in identifying trends its primary purpose has been in positioning trailing stop losses on open positions. We, however, explore if indeed it could be used as an Expert Advisor signal, thanks to custom signal classes of wizard assembled Expert Advisors.

This article presents a comprehensive guide to implementing a sophisticated trading system using Causality Network Analysis (CNA) and Vector Autoregression (VAR) in MQL5. It covers the theoretical background of these methods, provides detailed explanations of key functions in the trading algorithm, and includes example code for implementation.

Spatial Temporal Fusion which is using both ‘space’ and time metrics in modelling data is primarily useful in remote-sensing, and a host of other visual based activities in gaining a better understanding of our surroundings. Thanks to a published paper, we take a novel approach in using it by examining its potential to traders.

Time gap analysis helps traders identify potential market reversal points. The article discusses what a time gap is, how to interpret it, and how it can be used to detect large volume influxes into the market.

Symbolic Regression is a form of regression that starts with minimal to no assumptions on what the underlying model that maps the sets of data under study would look like. Even though it can be implemented by Bayesian Methods or Neural Networks, we look at how an implementation with Genetic Algorithms can help customize an expert signal class usable in the MQL5 wizard.

Build a local, bidirectional voice interface for MetaTrader 5 using MQL5 WebRequest and two Python services. The article implements offline speech recognition with Vosk, wake‑word detection, an HTTP command endpoint, and a text‑to‑speech server on localhost. You will wire an Expert Advisor that fetches commands, executes trades, and returns spoken confirmations for hands‑free operation.

This article presents a custom MQL5 money management class that adapts position sizing to real-time volatility using a monotonic queue for O(N) sliding-window extremes. The class applies inverse volatility scaling and optionally validates risk with an RBF network. We show implementation details in the Optimize method and compare results with the inbuilt Size-Optimized class to assess latency and risk control benefits.

This article will dive into methods to improve the expert's runtime in the strategy tester, the code will be written to divide news event times into hourly categories. These news event times will be accessed within their specified hour. This ensures that the EA can efficiently manage event-driven trades in both high and low-volatility environments.

Discover how to create exportable EX5 functions to efficiently query and save historical position data. In this step-by-step guide, we will expand the History Management EX5 library by developing modules that retrieve key properties of the most recently closed position. These include net profit, trade duration, pip-based stop loss, take profit, profit values, and various other important details.

This article extends the existing Flask backend to compute performance analytics from stored MetaTrader 5 closed trades and deliver them as both JSON and a simple web view. It calculates total trades, total profit, win rate, average profit, and trade duration metrics, returning JSON at /api/v1/analytics/summary and rendering a dashboard at /api/v1. The result provides a quick, consistent way to review trading performance from persisted SQLite records.

In this article, we will change the mouse pointer to enable the interaction with the control indicator to ensure reliable and stable operation.

This article is a continuation in a series that look at Category Theory implementation in MQL5. In here we examine how Graph-Theory could be integrated with monoids and other data structures when developing a close-out strategy to a trading system.

We continue to discuss the family of Decision Transformer methods. From previous article, we have already noticed that training the transformer underlying the architecture of these methods is a rather complex task and requires a large labeled dataset for training. In this article we will look at an algorithm for using unlabeled trajectories for preliminary model training.