Articles on machine learning in trading

This is an improved chaotic optimization algorithm (COA) that combines the effects of chaos with adaptive search mechanisms. The algorithm uses a set of chaotic maps and inertial components to explore the search space. The article reveals the theoretical foundations of chaotic methods of financial optimization.

The article considers a metaheuristic Artificial Ecosystem-based Optimization (AEO) algorithm, which simulates interactions between ecosystem components by creating an initial population of solutions and applying adaptive update strategies, and describes in detail the stages of AEO operation, including the consumption and decomposition phases, as well as different agent behavior strategies. The article introduces the features and advantages of this algorithm.

We follow up on our last article, where we introduced the indicator pair of the Ichimoku and the ADX, by looking at how this duo could be improved with Supervised Learning. Ichimoku and ADX are a support/resistance plus trend complimentary pairing. Our supervised learning approach uses a neural network that engages the Deep Spectral Mixture Kernel to fine tune the forecasts of this indicator pairing. As per usual, this is done in a custom signal class file that works with the MQL5 wizard to assemble an Expert Advisor.

Hidden Markov Models (HMMs) are a powerful class of probabilistic models designed to analyze sequential data, where observed events depend on some sequence of unobserved (hidden) states that form a Markov process. The main assumptions of HMM include the Markov property for hidden states, meaning that the probability of transition to the next state depends only on the current state, and the independence of observations given knowledge of the current hidden state.

The Deep-Q-Network is a reinforcement learning algorithm that engages neural networks in projecting the next Q-value and ideal action during the training process of a machine learning module. We have already considered an alternative reinforcement learning algorithm, Q-Learning. This article therefore presents another example of how an MLP trained with reinforcement learning, can be used within a custom signal class.

​This article integrates the Optuna hyperparameter optimization (HPO) backend into a unified ModelDevelopmentPipeline. It adds joint tuning of model hyperparameters and sample-weight schemes, early pruning with Hyperband, and crash-resistant SQLite study storage. The pipeline auto-detects primary vs. secondary models, prepends a fitted column-dropping preprocessor for safe inference, supports sequential bootstrapping, generates an Optuna report, and includes bid/ask and LearnedStrategy links. Readers get faster, resumable runs and deployable, self-contained models.

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.

This series of articles introduces several time series labeling methods, which can create data that meets most artificial intelligence models, and targeted data labeling according to needs can make the trained artificial intelligence model more in line with the expected design, improve the accuracy of our model, and even help the model make a qualitative leap!

In previous works, we always assessed the current state of the environment. At the same time, the dynamics of changes in indicators always remained "behind the scenes". In this article I want to introduce you to an algorithm that allows you to evaluate the direct change in data between 2 successive environmental states.

In the previous article, we got acquainted with one of the methods for detecting objects in an image. However, processing a static image is somewhat different from working with dynamic time series, such as the dynamics of the prices we analyze. In this article, we will consider the method of detecting objects in video, which is somewhat closer to the problem we are solving.

In this article, we revisit a classic crude oil trading strategy with the aim of enhancing it by leveraging supervised machine learning algorithms. We will construct a least-squares model to predict future Brent crude oil prices based on the spread between Brent and WTI crude oil prices. Our goal is to identify a leading indicator of future changes in Brent prices.

The FrAMA Indicator and the Force Index Oscillator are trend and volume tools that could be paired when developing an Expert Advisor. We continue from our last article that introduced this pair by considering machine learning applicability to the pair. We are using a convolution neural network that uses the dot-product kernel in making forecasts with these indicators’ inputs. This is done in a custom signal class file that works with the MQL5 wizard to assemble an Expert Advisor.

Artificial Cooperative Search (ACS) is an innovative method using a binary matrix and multiple dynamic populations based on mutualistic relationships and cooperation to find optimal solutions quickly and accurately. ACS unique approach to predators and prey enables it to achieve excellent results in numerical optimization problems.

In the world of big data, there are millions of alternative datasets that hold the potential to enhance our trading strategies. In this series of articles, we will help you identify the most informative public datasets.

Data classification for purposes of analysis and forecasting is a very diverse arena within machine learning and it features a large number of approaches and methods. This piece looks at one such approach, namely Agglomerative Hierarchical Classification.

Join us in our discussion as we look for additional improvements to make to our moving-average cross over strategy to reduce the lag in our trading strategy to more reliable levels by leveraging our skills in data science. It is a well-studied fact that projecting your data to higher dimensions can at times improve the performance of your machine learning models. We will demonstrate what this practically means for you as a trader, and illustrate how you can weaponize this powerful principle using your MetaTrader 5 Terminal.

Category Theory is a diverse and expanding branch of Mathematics which is only recently getting some coverage in the MQL5 community. These series of articles look to explore and examine some of its concepts & axioms with the overall goal of establishing an open library that provides insight while also hopefully furthering the use of this remarkable field in Traders' strategy development.

In this article, we will get acquainted with the ALGLIB library optimization methods for MQL5. The article includes simple and clear examples of using ALGLIB to solve optimization problems, which will make mastering the methods as accessible as possible. We will take a detailed look at the connection of such algorithms as BLEIC, L-BFGS and NS, and use them to solve a simple test problem.

The first part was devoted to the well-known and popular algorithm - simulated annealing. We have thoroughly considered its pros and cons. The second part of the article is devoted to the radical transformation of the algorithm, which turns it into a new optimization algorithm - Simulated Isotropic Annealing (SIA).

Time series forecasting in trading has evolved from traditional statistical models (like ARIMA) to deep learning approaches, but both require heavy tuning and training. Inspired by advances in NLP, Google’s TimesFM introduces a pretrained “foundation model” for time series that can perform strong forecasts even without task-specific training. For traders, this is powerful because it can be efficiently fine-tuned on their own data using lightweight methods like LoRA, reducing overfitting while adapting to changing market conditions.

In the last article, we examined the pairing of Ichimoku and the ADX under an Inference Learning framework. For this piece we revisit, Reinforcement Learning when used with an indicator pairing we considered last in ‘Part 68’. The TRIX and Williams Percent Range. Our algorithm for this review will be the Quantile Regression DQN. As usual, we present this as a custom signal class designed for implementation with the MQL5 Wizard.

In this article, we will discuss the Mask-Attention-Free Transformer (MAFT) method and its application in the field of trading. Unlike traditional Transformers that require data masking when processing sequences, MAFT optimizes the attention process by eliminating the need for masking, significantly improving computational efficiency.

We invite you to explore a framework that combines wavelet transforms and a multi-task self-attention model, aimed at improving the responsiveness and accuracy of forecasting in volatile market conditions. The wavelet transform allows asset returns to be decomposed into high and low frequencies, carefully capturing long-term market trends and short-term fluctuations.

As already explained in the theoretical part, when working with neural networks we need to use linear regressions and derivatives. Why? The reason is that linear regression is one of the simplest formulas in existence. Essentially, linear regression is just an affine function. However, when we talk about neural networks, we are not interested in the effects of direct linear regression. We are interested in the equation that generates this line. We are not that interested in the line created. Do you know the main equation that we need to understand? If not, I recommend reading this article to understanding it.

We continue our examination of the StockFormer hybrid trading system, which combines predictive coding and reinforcement learning algorithms for financial time series analysis. The system is based on three Transformer branches with a Diversified Multi-Head Attention (DMH-Attn) mechanism that enables the capturing of complex patterns and interdependencies between assets. Previously, we got acquainted with the theoretical aspects of the framework and implemented the DMH-Attn mechanisms. Today, we will talk about the model architecture and training.

We follow up on our last article, where we introduced the indicator couple of the Awesome-Oscillator and the Envelope Channel, by looking at how this pairing could be enhanced with Supervised Learning. The Awesome-Oscillator and Envelope-Channel are a trend-spotting and support/resistance complimentary mix. Our supervised learning approach is a CNN that engages the Dot Product Kernel with Cross-Time-Attention to size its kernels and channels. As per usual, this is done in a custom signal class file that works with the MQL5 wizard to assemble an Expert Advisor.

The article presents a complete Python–MQL5 integration for multi‑agent trading: MT5 data ingestion, indicator computation, per‑agent decisions, and a weighted consensus that outputs a single action. Signals are stored to JSON, served by Flask, and consumed by an MQL5 Expert Advisor for execution with position sizing and ATR‑derived SL/TP. Flask routes provide safe lifecycle control and status monitoring.

Monte-Carlo is the fourth different algorithm in reinforcement learning that we are considering with the aim of exploring its implementation in wizard assembled Expert Advisors. Though anchored in random sampling, it does present vast ways of simulation which we can look to exploit.

We continue our experiment that aims to examine the behavior of population optimization algorithms in the context of their ability to efficiently escape local minima when population diversity is low and reach global maxima. Research results are provided.

In this article, we will explore and implement, methods for assessing model quality that utilize a single dataset as both training and validation sets.

The CATCH framework combines Fourier transform and frequency patching to accurately identify market anomalies beyond the reach of traditional methods. Let us examine how this approach reveals hidden patterns in financial data.