Articles on trading system automation in MQL5

The article describes the theory and practice of applying the backpropagation algorithm in MQL5 using matrices. It provides ready-made classes along with script, indicator and Expert Advisor examples.

In this article, we apply a relatively complex neural network algorithm released in 2023 called PatchTST for predicting the price action for the next 24 hours. We will use the official repository, make slight modifications, train a model for EURUSD, and apply it to making future predictions both in Python and MQL5.

This article explores optimizing RSI levels and periods for better trading signals. We introduce methods to estimate optimal RSI values and automate period selection using grid search and statistical models. Finally, we implement the solution in MQL5 while leveraging Python for analysis. Our approach aims to be pragmatic and straightforward to help you solve potentially complicated problems, with simplicity.

Here is a new article about how to create a custom indicator. This time we will work with the True Strength Index (TSI) and will create an Expert Advisor based on it.

Even with a positive-expectancy system, position sizing determines whether you thrive or collapse. It’s the pivot of risk management—translating statistical edges into real-world results while safeguarding your capital.

This time, let's try a different approach to achieve the 1 minute goal. However, this task is not as simple as one might think.

Neural networks are an ultimate tool in traders' toolkit. Let's check if this assumption is true. MetaTrader 5 is approached as a self-sufficient medium for using neural networks in trading. A simple explanation is provided.

There is still one task which our order system is not up to, but we will FINALLY figure it out. The MetaTrader 5 provides a system of tickets which allows creating and correcting order values. The idea is to have an Expert Advisor that would make the same ticket system faster and more efficient.

In the previous article, we have created a class for data clustering. In this article, I want to share variants of the possible application of obtained results in solving practical trading tasks.

This article is about moral expectation. We will look at several examples of its use in trading, as well as the results that can be achieved with its help.

The Alligator Indicator, which was the brain child of Bill Williams, is a versatile trend identification indicator that yields clear signals and is often combined with other indicators. The MQL5 wizard classes and assembly allow us to test a variety of signals on a pattern basis, and so we consider this indicator as well.

In this article, we continue discussing methods for collecting data into a training set. Obviously, the learning process requires constant interaction with the environment. However, situations can be different.

Todays trader is a philomath who is almost always looking up new ideas, trying them out, choosing to modify them or discard them; an exploratory process that should cost a fair amount of diligence. These series of articles will proposition that the MQL5 wizard should be a mainstay for traders.

Unlike linear regression, polynomial regression is a flexible model aimed to perform better at tasks the linear regression model could not handle, Let's find out how to make polynomial models in MQL5 and make something positive out of it.

The Multi-Currency Expert Advisor in this article is Expert Advisor or trading robot that can trade (open orders, close orders and manage orders for example: Trailing Stop Loss and Trailing Profit) for more than one symbol pair only from one symbol chart. This time we will use only 1 indicator, namely Triangular moving average in multi-timeframes or single timeframe.

We continue to consider the clustering method. In this article, we will create a new CKmeans class to implement one of the most common k-means clustering methods. During tests, the model managed to identify about 500 patterns.

In this article, I will use experimentation and non-standard approaches to develop a profitable trading system and check whether neural networks can be of any help for traders. MetaTrader 5 as a self-sufficient tool for using neural networks in trading.

Moving average cross-overs are widely known by traders in our community, and yet the core of the strategy has changed very little since its inception. In this discussion, we will present you with a slight adjustment to the original strategy, that aims to minimize the lag present in the trading strategy. All fans of the original strategy, could consider revising the strategy in accordance with the insights we will discuss today. By using 2 moving averages with the same period, we reduce the lag in the trading strategy considerably, without violating the foundational principles of the strategy.

The gradient descent plays a significant role in training neural networks and many machine learning algorithms. It is a quick and intelligent algorithm despite its impressive work it is still misunderstood by a lot of data scientists let's see what it is all about.

In this article, we build a multi-timeframe scanner dashboard in MQL5 to display real-time trading signals. We plan an interactive grid interface, implement signal calculations with multiple indicators, and add a close button. The article concludes with backtesting and strategic trading benefits

Today we will construct the second part of the Times & Trade system for market analysis. In the previous article "Times & Trade (I)" we discussed an alternative chart organization system, which would allow having an indicator for the quickest possible interpretation of deals executed in the market.

Developing a trading robot based on machine learning: A detailed guide. The first article in the series deals with collecting and preparing data and features. The project is implemented using the Python programming language and libraries, as well as the MetaTrader 5 platform.

In Part 38, we build a production-grade MT5 monitoring panel that converts raw ticks into actionable signals. The EA buffers tick data to compute tick-level VWAP, a short-window imbalance (flow) metric, and ATR-based position sizing. It then visualizes spread, ATR, and flow with low-flicker bars. The system calculates a suggested lot size and a 1R stop, and issues configurable alerts for tight spreads, strong flow, and edge conditions. Auto-trading is intentionally disabled; the focus remains on robust signal generation and a clean user experience.

This article continues the topic of predicting the upcoming price movement. I invite you to get acquainted with the Multi-future Transformer architecture. Its main idea is to decompose the multimodal distribution of the future into several unimodal distributions, which allows you to effectively simulate various models of interaction between agents on the scene.

Several fellow traders sent emails or commented about how to use this Multi-Currency EA on brokers with symbol names that have prefixes and/or suffixes, and also how to implement trading time zones or trading time sessions on this Multi-Currency EA.

The Darvas Box Breakout Strategy, created by Nicolas Darvas, is a technical trading approach that spots potential buy signals when a stock’s price rises above a set "box" range, suggesting strong upward momentum. In this article, we will apply this strategy concept as an example to explore three advanced machine learning techniques. These include using a machine learning model to generate signals rather than to filter trades, employing continuous signals rather than discrete ones, and using models trained on different timeframes to confirm trades.