Articles with examples of trading robots developed in MQL5

In the previous article, we introduced the DDPG method, which allows training models in a continuous action space. However, like other Q-learning methods, DDPG is prone to overestimating Q-function values. This problem often results in training an agent with a suboptimal strategy. In this article, we will look at some approaches to overcome the mentioned issue.

Forecasting plays an important role in time series analysis. In the new article, we will talk about the benefits of time series patching.

We invite you to get acquainted with the Hierarchical Vector Transformer (HiVT) method, which was developed for fast and accurate forecasting of multimodal time series.

In this article, we upgrade our Trade Assistant Tool by adding drag-and-drop panel functionality and hover effects to make the interface more intuitive and responsive. We refine the tool to validate real-time order setups, ensuring accurate trade configurations relative to market prices. We also backtest these enhancements to confirm their reliability.

The use of anisotropic diffusion processes for encoding the initial data in a hyperbolic latent space, as proposed in the HypDIff framework, assists in preserving the topological features of the current market situation and improves the quality of its analysis. In the previous article, we started implementing the proposed approaches using MQL5. Today we will continue the work we started and will bring it to its logical conclusion.

This project explores the fusion of deep learning and technical analysis to test trading strategies in forex. A Python script is used for rapid experimentation, employing an ONNX model alongside traditional indicators like PSAR, SMA, and RSI to predict EUR/USD movements. A MetaTrader 5 script then brings this strategy into a live environment, using historical data and technical analysis to make informed trading decisions. The backtesting results indicate a cautious yet consistent approach, with a focus on risk management and steady growth rather than aggressive profit-seeking.

Trading strategies may be challenging to improve because we often don’t fully understand what the strategy is doing wrong. In this discussion, we introduce linear system identification, a branch of control theory. Linear feedback systems can learn from data to identify a system’s errors and guide its behavior toward intended outcomes. While these methods may not provide fully interpretable explanations, they are far more valuable than having no control system at all. Let’s explore linear system identification and observe how it may help us as algorithmic traders to maintain control over our trading applications.

In this article news filtration for individual news events based on their IDs will be implemented. In addition, previous SQL queries will be improved to provide additional information or reduce the query's runtime. Furthermore, the code built in the previous articles will be made functional.

SAMformer offers a solution to the key drawbacks of Transformer models in long-term time series forecasting, such as training complexity and poor generalization on small datasets. Its shallow architecture and sharpness-aware optimization help avoid suboptimal local minima. In this article, we will continue to implement approaches using MQL5 and evaluate their practical value.

This article explores a trading strategy that integrates Linear Discriminant Analysis (LDA) with Bollinger Bands, leveraging categorical zone predictions for strategic market entry signals.

In this article, we continue the implementation of the approaches of the ATFNet model, which adaptively combines the results of 2 blocks (frequency and time) within time series forecasting.

The authors of the FreDF method experimentally confirmed the advantage of combined forecasting in the frequency and time domains. However, the use of the weight hyperparameter is not optimal for non-stationary time series. In this article, we will get acquainted with the method of adaptive combination of forecasts in frequency and time domains.

We continue studying distributed Q-learning algorithms. In previous articles, we have considered distributed and quantile Q-learning algorithms. In the first algorithm, we trained the probabilities of given ranges of values. In the second algorithm, we trained ranges with a given probability. In both of them, we used a priori knowledge of one distribution and trained another one. In this article, we will consider an algorithm which allows the model to train for both distributions.

In this article, we will make an attempt to develop our own trading strategy. Any trading strategy must be based on some kind of statistical advantage. Moreover, this advantage should exist for a long time.

In the previous article, we introduced the multi-agent self-adaptive framework MASA, which combines reinforcement learning approaches and self-adaptive strategies, providing a harmonious balance between profitability and risk in turbulent market conditions. We have built the functionality of individual agents within this framework. In this article, we will continue the work we started, bringing it to its logical conclusion.

In this series article, we will empirically analyze classic trading strategies to see if we can improve them using AI. In today's discussion, we tried to predict higher highs and lower lows using the Linear Discriminant Analysis model.

Discover how to effortlessly import and utilize the History Manager EX5 library in your MQL5 source code to process trade histories in your MetaTrader 5 account in this series' final article. With simple one-line function calls in MQL5, you can efficiently manage and analyze your trading data. Additionally, you will learn how to create different trade history analytics scripts and develop a price-based Expert Advisor as practical use-case examples. The example EA leverages price data and the History Manager EX5 library to make informed trading decisions, adjust trade volumes, and implement recovery strategies based on previously closed trades.

The previously developed risk manager contained only basic functionality. Let's try to consider possible ways of its development, allowing us to improve trading results without interfering with the logic of trading strategies.

Algorithmic trading system that combines volume analysis with machine learning techniques, specifically LSTM neural networks. Unlike traditional trading approaches that primarily focus on price movements, this system emphasizes volume patterns and their derivatives to predict market movements. The methodology incorporates three main components: volume derivatives analysis (first and second derivatives), LSTM predictions for volume patterns, and traditional technical indicators.

How does portfolio trading work on Forex? How can Markowitz portfolio theory for portfolio proportion optimization and VaR model for portfolio risk optimization be synthesized? We create a code based on portfolio theory, where, on the one hand, we will get low risk, and on the other, acceptable long-term profitability.

Having started developing a multi-currency EA, we have already achieved some results and managed to carry out several code improvement iterations. However, our EA was unable to work with pending orders and resume operation after the terminal restart. Let's add these features.

Today, we delve into incorporating useful trading metrics within a specialized window integrated into the Admin Panel EA. This discussion focuses on the implementation of MQL5 to develop an Analytics Panel and highlights the value of the data it provides to trading administrators. The impact is largely educational, as valuable lessons are drawn from the development process, benefiting both upcoming and experienced developers. This feature demonstrates the limitless opportunities this development series offers in equipping trade managers with advanced software tools. Additionally, we'll explore the implementation of the PieChart and ChartCanvas classes as part of the continued expansion of the Trading Administrator panel’s capabilities.

Since the first articles devoted to reinforcement learning, we have in one way or another touched upon 2 problems: exploring the environment and determining the reward function. Recent articles have been devoted to the problem of exploration in offline learning. In this article, I would like to introduce you to an algorithm whose authors completely eliminated the reward function.

We continue our acquaintance with the TEMPO method. In this article we will evaluate the actual effectiveness of the proposed approaches on real historical data.

In the previous parts, the Expert Advisor (EA) under development was able to use only a fixed position size for trading. This is acceptable for testing, but is not advisable when trading on a real account. Let's make it possible to trade using variable position sizes.

Points of support and resistance are critical levels that signal potential trend reversals and continuations. Although identifying these levels can be challenging, once you pinpoint them, you’re well-prepared to navigate the market. For further assistance, check out the Quarters Drawer tool featured in this article, it will help you identify both primary and minor support and resistance levels.

This article focuses on essential MQL5 file-handling techniques, spanning trade logs, CSV processing, and external data integration. It offers both conceptual understanding and hands-on coding guidance. Readers will learn to build a custom CSV importer class step-by-step, gaining practical skills for real-world applications.