Articles on the MQL5 programming and use of trading robots

After improving the C_Mouse class, we can focus on creating a class designed to create a completely new framework fr our analysis. We will not use inheritance or polymorphism to create this new class. Instead, we will change, or better said, add new objects to the price line. That's what we will do in this article. In the next one, we will look at how to change the analysis. All this will be done without changing the code of the C_Mouse class. Well, actually, it would be easier to achieve this using inheritance or polymorphism. However, there are other methods to achieve the same result.

By studying the FEDformer method, we opened the door to the frequency domain of time series representation. In this new article, we will continue the topic we started. We will consider a method with which we can not only conduct an analysis, but also predict subsequent states in a particular area.

While analyzing the market situation, we divide it into separate segments, identifying key trends. However, traditional analysis methods often focus on one aspect and thus limit the proper perception. In this article, we will learn about a method that enables the selection of multiple objects to ensure a more comprehensive and multi-layered understanding of the situation.

In this article, we will discuss another type of models that are aimed at studying the dynamics of the environmental state.

In the previous article, we got acquainted with the Decision Transformer. But the complex stochastic environment of the foreign exchange market did not allow us to fully implement the potential of the presented method. In this article, I will introduce an algorithm that is aimed at improving the performance of algorithms in stochastic environments.

We add supersampling‑driven anti‑aliasing and high‑resolution rendering to the MQL5 canvas dashboard, then downsample to the target size. The article implements rounded rectangle fills and borders, rounded triangle arrows, and a custom scrollbar with theming for the stats and text panels. These tools help you build smoother, more legible UI components in MetaTrader 5.

We continue to build the Hidformer hierarchical dual-tower transformer model designed for analyzing and forecasting complex multivariate time series. In this article, we will bring the work we started earlier to its logical conclusion — we will test the model on real historical data.

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 explores why trading results can differ significantly between brokers, even when using the same strategy and financial symbol, due to decentralized pricing and data discrepancies. The piece helps MQL5 developers understand why their products may receive mixed reviews on the MQL5 Marketplace, and urges developers to tailor their approaches to specific brokers to ensure transparent and reproducible outcomes. This could grow to become an important domain-bound best practice that will serve our community well if the practice were to be widely adopted.

Explore how Vector Autoregression (VAR) models can forecast Forex OHLC (Open, High, Low, and Close) time series data. This article covers VAR implementation, model training, and real-time forecasting in MetaTrader 5, helping traders analyze interdependent currency movements and improve their trading strategies.

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.

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.

The article presents two systematic pitfalls in MQL5 multi‑timeframe work: indicator handle leaks that exhausted resources and repainting from reading the forming bar (index 0). It introduces MTFEngine.mqh, a unified include that creates and tracks handles in one place and defaults all reads to closed bars (index 1). A D1–H4–H1 example shows how this approach keeps signals technically correct and consistent with charts.

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 follow up our last article, where we introduced the indicator pair of TRIX and Williams Percent Range, by considering how this indicator pairing could be extended with Machine Learning. TRIX and William’s Percent are a trend and support/ resistance complimentary pairing. Our machine learning approach uses a convolution neural network that engages the cosine kernel in its architecture when fine-tuning the forecasts of this indicator pairing. As always, this is done in a custom signal class file that works with the MQL5 wizard to assemble an Expert Advisor.

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.

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.

Soft Actor Critic is a Reinforcement Learning algorithm that we looked at in a previous article, where we also introduced python and ONNX to these series as efficient approaches to training networks. We revisit the algorithm with the aim of exploiting tensors, computational graphs that are often exploited in Python.

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 shows how to build a local stop-loss system in an MQL5 Expert Advisor that keeps stop levels on the terminal side. It walks through the execution logic, event handlers, inputs, and an OOP design using CTrade, CPositionInfo, CHashMap/CHashSet, and chart objects. You will implement multi-position tracking, draggable stops, visual spacers and labels, plus cleanup and disconnection behavior to create a practical risk-control utility.

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.

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 demonstrates how to build the persistence foundation of a self-healing Expert Advisor in MQL5 using SQLite. Readers will learn how to create a permanent trade-state storage layer capable of surviving terminal restarts, shutdowns, and unexpected interruptions. The article covers SQLite integration in MetaTrader 5, database lifecycle management, persistent trade-state structures, and runtime state recovery using practical MQL5 implementations.

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.

This piece follows up ‘Part-80’, where we examined the pairing of Ichimoku and the ADX under a Reinforcement Learning framework. We now shift focus to Inference Learning. Ichimoku and ADX are complimentary as already covered, however we are going to revisit the conclusions of the last article related to pipeline use. For our inference learning, we are using the Beta algorithm of a Variational Auto Encoder. We also stick with the implementation of a custom signal class designed for integration with the MQL5 Wizard.

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.

This is a continuation of the previous article considering the idea of social groups. The article explores the evolution of social groups using movement and memory algorithms. The results will help to understand the evolution of social systems and apply them in optimization and search for solutions.