Articles on trading system automation in MQL5

In this article, we will look at how to lock the indicator while simply using the MQL5 language, and we will do it in a very interesting and amazing way.

The article enhances an MQL5 footprint indicator with a compact box above each candle that summarizes net delta, total volume, and buy/sell percentages. We implement supersampled anti‑aliased rendering, rounded corners via arc and quadrilateral rasterization, and per‑pixel alpha compositing. Supporting utilities include ARGB conversion, scanline fills, and box‑filter downsampling. The box delivers fast sentiment reads that stay legible across zoom levels.

We have already created quite a few components that help arrange auto optimization. During the creation, we followed the traditional cyclical structure: from creating minimal working code to refactoring and obtaining improved code. It is time to start clearing up our database, which is also a key component in the system we are creating.

Today we will remove a limitation that has been preventing simulations based on the Last price and will introduce a new entry point specifically for this type of simulation. The entire operating mechanism will be based on the principles of the forex market. The main difference in this procedure is the separation of Bid and Last simulations. However, it is important to note that the methodology used to randomize the time and adjust it to be compatible with the C_Replay class remains identical in both simulations. This is good because changes in one mode lead to automatic improvements in the other, especially when it comes to handling time between ticks.

This article introduces the Conformer algorithm originally developed for the purpose of weather forecasting, which in terms of variability and capriciousness can be compared to financial markets. Conformer is a complex method. It combines the advantages of attention models and ordinary differential equations.

We determine the overbought and oversold condition of the market according to chaos theory: integrating the principles of chaos theory, fractal geometry and neural networks to forecast financial markets. The study demonstrates the use of the Lyapunov exponent as a measure of market randomness and the dynamic adaptation of trading signals. The methodology includes an algorithm for generating fractal noise, hyperbolic tangent activation, and moment optimization.

Do you want to know how to benefit from the difference in interest rates? This article considers how to use swap arbitrage in Forex to earn stable profit every night, creating a portfolio that is resistant to market fluctuations.

In previous articles, we discussed the Decision Transformer method and several algorithms derived from it. We experimented with different goal setting methods. During the experiments, we worked with various ways of setting goals. However, the model's study of the earlier passed trajectory always remained outside our attention. In this article. I want to introduce you to a method that fills this gap.

Soft Actor Critic is a Reinforcement Learning algorithm that utilizes 3 neural networks. An actor network and 2 critic networks. These machine learning models are paired in a master slave partnership where the critics are modelled to improve the forecast accuracy of the actor network. While also introducing ONNX in these series, we explore how these ideas could be put to test as a custom signal of a wizard assembled Expert Advisor.

This article presents two versions of the Crystal Structure Algorithm: the original and the modified version. The Crystal Structure Algorithm (CryStAl), published in 2021 and inspired by the physics of crystal structures, was positioned as a parameter-free metaheuristic for global optimization. However, testing revealed a critical problem with the algorithm. A modified version, CryStAlm, is also presented; it addresses the original's key shortcomings.

We follow up on our last article, where we introduced the indicator pair of the MACD and the OBV, by looking at how this pairing could be enhanced with Machine Learning. MACD and OBV are a trend and volume complimentary pairing. Our machine learning approach uses a convolution neural network that engages the Exponential kernel in sizing its kernels and channels, 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.

The article outlines a practical data pipeline for quantitative analysis based on Parquet storage, Hive-style partitions, and DuckDB. It details migrating selected SQLite tables to Parquet, structuring market data by source, symbol, timeframe, and date, and querying it with SQL window functions. A Golden Cross example illustrates cross‑symbol evaluation of forward returns. Accompanying Python scripts handle data download, conversion, and execution.

In this article, I would like to introduce you to an interesting trajectory prediction method developed to solve problems in the field of autonomous vehicle movements. The authors of the method combined the best elements of various architectural solutions.

This is an article about a specialized trend-following EA that aims to clearly elaborate how to utilize trading setups after liquidity raids. This article will explore in detail an EA that is specifically designed for traders who are keen on optimizing and utilizing liquidity raids and purges as entry criteria for their trades and trading decisions. It will also explore how to correctly differentiate between liquidity raids and market structure shifts and how to validate and utilize each of them when they occur, thus trying to mitigate losses that occur from traders confusing the two.

Let's create something more interesting. I don't want to spoil the surprise, so follow the article for a better understanding. From the very beginning of this series on developing the replay/simulator system, I was saying that the idea is to use the MetaTrader 5 platform in the same way both in the system we are developing and in the real market. It is important that this is done properly. No one wants to train and learn to fight using one tool while having to use another one during the fight.

The article discusses the application of Walsh functions in trading. We will explore the basic principles of using these functions to analyze financial markets, forecast prices, and make trading decisions. We will also discuss the advantages and disadvantages of these functions, as well as the prospects for their application in trading and technical analysis.

Meet Mantis — a lightweight foundation model for time series classification based on a Transformer architecture, featuring contrastive pre-training and hybrid attention that deliver record-breaking accuracy and scalability.

In this article, we will attempt to predict the market with a decent model for time series forecasting named DeepAR. A model that is a combination of deep neural networks and autoregressive properties found in models like ARIMA and Vector Autoregressive (VAR).

Transformer architecture-based models demonstrate high efficiency, but their use is complicated by high resource costs both at the training stage and during operation. In this article, I propose to get acquainted with algorithms that allow to reduce memory usage of such models.

In the context of reinforcement learning, model procrastination can be caused by several reasons. The article considers some of the possible causes of model procrastination and methods for overcoming them.

In this article, we discuss Directional Diffusion Models that exploit data-dependent anisotropic and directed noise in a forward diffusion process to capture meaningful graph representations.

In the last piece, we concluded our look at the pairing of the gator oscillator and the accumulation/distribution oscillator when used in their typical setting of the raw signals they generate. These two indicators are complimentary as trend and volume indicators, respectively. We now follow up that piece, by examining the effect that supervised learning can have on enhancing some of the feature patterns we had reviewed. Our supervised learning approach is a CNN that engages with kernel regression and dot product similarity to size its kernels and channels. As always, we do this in a custom signal class file that works with the MQL5 wizard to assemble an Expert Advisor.

We continue to build the algorithms that form the basis of the DADA framework, which is an advanced tool for detecting anomalies in time series. This approach enables effective distinguishing random fluctuations from significant deviations. Unlike classical methods, DADA dynamically adapts to different data types, choosing the optimal compression level in each specific case.

In this article, we will examine the application of mathematics to grid strategies. We will consider the basic principles of the strategy, as well as its advantages and disadvantages. You will learn how to build a trading grid, set optimal parameters, and manage risks effectively.

In this article, we develop a custom indicator in MQL5 for hybrid Time Price Opportunity (TPO) market profiles, supporting multiple session timeframes such as intraday, daily, weekly, monthly, and fixed periods with timezone adjustments. The indicator quantizes prices into a grid, tracks session data including highs, lows, opens, and closes, and calculates key elements like the point of control and value area based on TPO counts. It renders profiles visually on the chart with customizable colors for TPO letters, single prints, value areas, POC, and close markers, enabling detailed session analysis

Here I will consider the fairly new Stochastic Marginal Actor-Critic (SMAC) algorithm, which allows building latent variable policies within the framework of entropy maximization.

The Awesome Oscillator is another Bill Williams Indicator that is used to measure momentum. It can generate multiple signals, and therefore we review these on a pattern basis, as in prior articles, by capitalizing on the MQL5 wizard classes and assembly.

We invite you to get acquainted with the DADA framework, which is an innovative method for detecting anomalies in time series. It helps distinguish random fluctuations from suspicious deviations. Unlike traditional methods, DADA is flexible and adapts to different data. Instead of a fixed compression level, it uses several options and chooses the most appropriate one for each case.

The Learning Rate, is a step size towards a training target in many machine learning algorithms’ training processes. We examine the impact its many schedules and formats can have on the performance of a Generative Adversarial Network, a type of neural network that we had examined in an earlier article.

Economic Calendar Data is not available for testing with Expert Advisors within Strategy Tester, by default. We look at how Databases could help in providing a work around this limitation. So, for this article we explore how SQLite databases can be used to archive Economic Calendar news such that wizard assembled Expert Advisors can use this to generate trade signals.

Today we will begin the second stage, where we will look at the market replay/simulation system. First, we will show a possible solution for cross orders. I will show you the solution, but it is not final yet. It will be a possible solution to a problem that we will need to solve in the near future.

When exploring various model architecture designs, we often devote insufficient attention to the process of model training. In this article, I aim to address this gap.

In this article. we will discuss a method of complex multimodal interaction analysis and feature understanding.

Now the creation occurs at the same point where we converted ticks into bars. This way, if something goes wrong during the conversion process, we will immediately notice the error. This is because the same code that places 1-minute bars on the chart during fast forwarding is also used for the positioning system to place bars during normal performance. In other words, the code that is responsible for this task is not duplicated anywhere else. This way we get a much better system for both maintenance and improvement.

This article tests three common filters on a standard MACD crossover for US_TECH100 H1 using five years of broker-native data. Filters are layered incrementally: regime, higher timeframe (HTF) alignment, and US session timing, to isolate each one's marginal impact. Results show session timing contributes far more than indicator refinements, while regime and HTF add little on their own. Includes a reproducible MQL5 regime classifier.