Articles on trading system automation in MQL5

Clustering algorithms in machine learning are important unsupervised learning algorithms that can divide the original data into groups with similar observations. By using these groups, you can analyze the market for a specific cluster, search for the most stable clusters using new data, and make causal inferences. The article proposes an original method for time series clustering in Python.

We continue our dive into chaos theory in financial markets. This time I will consider its applicability to the analysis of currencies and other assets.

Larry Connors is a renowned trader and author, best known for his work in quantitative trading and strategies like the 2-period RSI (RSI2), which helps identify short-term overbought and oversold market conditions. In this article, we’ll first explain the motivation behind our research, then recreate three of Connors’ most famous strategies in MQL5 and apply them to intraday trading of the S&P 500 index CFD.

Restricted Boltzmann Machines are a form of neural network that was developed in the mid 1980s at a time when compute resources were prohibitively expensive. At its onset, it relied on Gibbs Sampling and Contrastive Divergence in order to reduce dimensionality or capture the hidden probabilities/properties over input training data sets. We examine how Backpropagation can perform similarly when the RBM ‘embeds’ prices for a forecasting Multi-Layer-Perceptron.

The article examines the topic of matching in causal inference. Matching is used to compare similar observations in a data set. This is necessary to correctly determine causal effects and get rid of bias. The author explains how this helps in building trading systems based on machine learning, which become more stable on new data they were not trained on. The propensity score plays a central role and is widely used in causal inference.

Previously, we evaluated the selection of a group of trading strategy instances, with the aim of improving the results of their joint operation, only on the same time period, in which the optimization of individual instances was carried out. Let's see what happens in the forward period.

Let's outline the main stages of the EA development. One of the first things to be done will be to optimize a single instance of the developed trading strategy. Let's try to collect all the necessary information about the tester passes during the optimization in one place.

Tired of wasting time searching for that very file that you application needs in order to work? How about including everything in the executable? This way you won't have to search for the things. I know that many people use this form of distribution and storage, but there is a much more suitable way. At least as far as the distribution of executable files and their storage is concerned. The method that will be presented here can be very useful, since you can use MetaTrader 5 itself as an excellent assistant, as well as MQL5. Furthermore, it is not that difficult to understand.

Most people who want or dream of learning to program don't actually have a clue what they're doing. Their activity consists of trying to create things in a certain way. However, programming is not about tailoring suitable solutions. Doing it this way can create more problems than solutions. Here we will be doing something more advanced and therefore different.

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.

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.

In our series on integrating MQL5 with data processing packages, we delve in to the powerful combination of machine learning and predictive analysis. We will explore how to seamlessly connect MQL5 with popular machine learning libraries, to enable sophisticated predictive models for financial markets.

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.

In this article, we introduce the development of an interactive Trade Assistant Tool in MQL5, designed to simplify placing pending orders in Forex trading. We outline the conceptual design, focusing on a user-friendly GUI for setting entry, stop-loss, and take-profit levels visually on the chart. Additionally, we detail the MQL5 implementation and backtesting process to ensure the tool’s reliability, setting the stage for advanced features in the preceding parts.

With the rapid development of artificial intelligence today, language models (LLMs) are an important part of artificial intelligence, so we should think about how to integrate powerful LLMs into our algorithmic trading. For most people, it is difficult to fine-tune these powerful models according to their needs, deploy them locally, and then apply them to algorithmic trading. This series of articles will take a step-by-step approach to achieve this goal.

For decades, traders have been using the Kelly Criterion formula to determine the optimal proportion of capital to allocate to an investment or bet to maximize long-term growth while minimizing the risk of ruin. However, blindly following Kelly Criterion using the result of a single backtest is often dangerous for individual traders, as in live trading, trading edge diminishes over time, and past performance is no predictor of future result. In this article, I will present a realistic approach to applying the Kelly Criterion for one or more EA's risk allocation in MetaTrader 5, incorporating Monte Carlo simulation results from Python.

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.

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.

Regularization is a form of penalizing the loss function in proportion to the discrete weighting applied throughout the various layers of a neural network. We look at the significance, for some of the various regularization forms, this can have in test runs with a wizard assembled Expert Advisor.

All the models we have considered so far analyze the state of the environment as a time sequence. However, the time series can also be represented in the form of frequency features. In this article, I introduce you to an algorithm that uses frequency components of a time sequence to predict future states.

Proximal Policy Optimization is another algorithm in reinforcement learning that updates the policy, often in network form, in very small incremental steps to ensure the model stability. We examine how this could be of use, as we have with previous articles, in a wizard assembled Expert Advisor.

In this article we present an algorithm for permuting price bars and detail how permutation tests can be used to recognize instances where strategy performance has been fabricated to deceive potential buyers of Expert Advisors.

Most modern multimodal time series forecasting methods use the independent channels approach. This ignores the natural dependence of different channels of the same time series. Smart use of two approaches (independent and mixed channels) is the key to improving the performance of the models.

Here we are going to develop a script from scratch that simplifies unloading print screens of deals for analyzing trading entries. All the necessary information on a single deal is to be conveniently displayed on one chart with the ability to draw different timeframes.

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.

Portfolio Diversification and Optimization strategically spreads investments across multiple assets to minimize risk while selecting the ideal asset mix to maximize returns based on risk-adjusted performance metrics.

Strategies that are based on multiple time frames cannot be tested in wizard assembled Expert Advisors by default because of the MQL5 code architecture used in the assembly classes. We explore a possible work around this limitation for strategies that look to use multiple time frames in a case study with the quadratic moving average.

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

The Fractals by Bill Williams is a potent indicator that is easy to overlook when one initially spots it on a price chart. It appears too busy and probably not incisive enough. We aim to draw away this curtain on this indicator by examining what its various patterns could accomplish when examined with forward walk tests on all, with wizard assembled Expert Advisor.

Direct point cloud analysis avoids unnecessary data growth and improves the performance of models in classification and segmentation tasks. Such approaches demonstrate high performance and robustness to perturbations in the original data.

This article details creating an MQL5 Market Regime Detection System using statistical methods like autocorrelation and volatility. It provides code for classes to classify trending, ranging, and volatile conditions and a custom indicator.

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.

Effective identification and preservation of the local structure of market data in noisy conditions is a critical task in trading. The use of the Self-Attention mechanism has shown promising results in processing such data; however, the classical approach does not account for the local characteristics of the underlying structure. In this article, I introduce an algorithm capable of incorporating these structural dependencies.