Articles on machine learning in trading

In this second installment of the MetaTrader 5 Machine Learning Blueprint series, you’ll discover why simple labels can lead your models astray—and how to apply advanced techniques like the Triple-Barrier and Trend-Scanning methods to define robust, risk-aware targets. Packed with practical Python examples that optimize these computationally intensive techniques, this hands-on guide shows you how to transform noisy market data into reliable labels that mirror real-world trading conditions.

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.

This article explores the powerful role of matrix factorization in algorithmic trading, specifically within MQL5 applications. From regression models to multi-target classifiers, we walk through practical examples that demonstrate how easily these techniques can be integrated using built-in MQL5 functions. Whether you're predicting price direction or modeling indicator behavior, this guide lays a strong foundation for building intelligent trading systems using matrix methods.

In the previous work, we discussed the theoretical aspects of the PSformer framework, which includes two major innovations in the classical Transformer architecture: the Parameter Shared (PS) mechanism and attention to spatio-temporal segments (SegAtt). In this article, we continue the work we started on implementing the proposed approaches using MQL5.

Harness the full potential of your MetaTrader 5 terminal by leveraging Python’s data-science ecosystem and the official MetaTrader 5 client library. This article demonstrates how to authenticate and stream live tick and minute-bar data directly into Parquet storage, apply sophisticated feature engineering with Ta and Prophet, and train a time-aware Gradient Boosting model. We then deploy a lightweight Flask service to serve trade signals in real time. Whether you’re building a hybrid quant framework or enhancing your EA with machine learning, you’ll walk away with a robust, end-to-end pipeline for data-driven algorithmic trading.

This article introduces the new PSformer framework, which adapts the architecture of the vanilla Transformer to solving problems related to multivariate time series forecasting. The framework is based on two key innovations: the Parameter Sharing (PS) mechanism and the Segment Attention (SegAtt).

This part focuses on building a flexible, adaptive trading model trained on historical XAUUSD data, preparing it for ONNX export and potential integration into live trading systems.

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.

The article presents a simple and accessible way to use a neural network in a trading EA that does not require deep knowledge of machine learning. The method eliminates the target function normalization, as well as overcomes "weight explosion" and "network stall" issues offering intuitive training and visual control of the results.

Discovering a new world of automated trading on 3D bars. What does a trading robot look like on multidimensional price bars? Are "yellow" clusters of 3D bars able to predict trend reversals? What does multidimensional trading look like?

Have you ever missed a sudden market spike or been caught off‑guard when one occurred? The best way to anticipate live events is to learn from historical patterns. Intending to train an ML model, this article begins by showing you how to create a script in MetaTrader 5 that ingests historical data and sends it to Python for storage—laying the foundation for your spike‑detection system. Read on to see each step in action.

The article presents the transformation of the well-known and popular ADAM gradient optimization method into a population algorithm and its modification with the introduction of hybrid individuals. The new approach allows creating agents that combine elements of successful decisions using probability distribution. The key innovation is the formation of hybrid population individuals that adaptively accumulate information from the most promising solutions, increasing the efficiency of search in complex multidimensional spaces.

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.

Training Transformer models requires large amounts of data and is often difficult since the models are not good at generalizing to small datasets. The SAMformer framework helps solve this problem by avoiding poor local minima. This improves the efficiency of models even on limited training datasets.

N-BEATS is a revolutionary deep learning model designed for time series forecasting. It was released to surpass classical models for time series forecasting such as ARIMA, PROPHET, VAR, etc. In this article, we are going to discuss this model and use it in predicting the stock market.

The LSEAttention framework offers improvements to the Transformer architecture. It was designed specifically for long-term multivariate time series forecasting. The approaches proposed by the authors of the method can be applied to solve problems of entropy collapse and learning instability, which are often encountered with vanilla Transformer.

Non-linear regression models on the stock exchange: Is it possible to predict financial markets? Let's consider creating a model for forecasting prices for EURUSD, and make two robots based on it - in Python and MQL5.

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.

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.

In this article, we present the Arithmetic Optimization Algorithm (AOA) based on simple arithmetic operations: addition, subtraction, multiplication and division. These basic mathematical operations serve as the foundation for finding optimal solutions to various problems.

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.

In this article, we enhance a neural network trading strategy in MQL5 with an adaptive learning rate to boost accuracy. We design and implement this mechanism, then test its performance. The article concludes with optimization insights for algorithmic trading.

In the second part of the article, we will continue developing a modified version of the AOS (Atomic Orbital Search) algorithm focusing on specific operators to improve its efficiency and adaptability. After analyzing the fundamentals and mechanics of the algorithm, we will discuss ideas for improving its performance and the ability to analyze complex solution spaces, proposing new approaches to extend its functionality as an optimization tool.

The article explores the possibility of improving price forecasting based on trading volume analysis by integrating technical analysis principles with LSTM neural network architecture. Particular attention is paid to the detection and interpretation of anomalous volumes, the use of clustering and the creation of features based on volumes and their definition in the context of machine learning.

Join us for our follow-up discussion, where we will merge our first two trading strategies into an ensemble trading strategy. We shall demonstrate the different schemes possible for combining multiple strategies and also how to exercise control over the parameter space, to ensure that effective optimization remains possible even as our parameter size grows.

The article implements a fast strategy tester for machine learning models using Numba. It is 50 times faster than the pure Python strategy tester. The author recommends using this library to speed up mathematical calculations, especially the ones involving loops.

Before we can even begin to make use of ML in our trading on MetaTrader 5, it’s crucial to address one of the most overlooked pitfalls—data leakage. This article unpacks how data leakage, particularly the MetaTrader 5 timestamp trap, can distort our model's performance and lead to unreliable trading signals. By diving into the mechanics of this issue and presenting strategies to prevent it, we pave the way for building robust machine learning models that deliver trustworthy predictions in live trading environments.

The article considers the Atomic Orbital Search (AOS) algorithm, which uses the concepts of the atomic orbital model to simulate the search for solutions. The algorithm is based on probability distributions and the dynamics of interactions in the atom. The article discusses in detail the mathematical aspects of AOS, including updating the positions of candidate solutions and the mechanisms of energy absorption and release. AOS opens new horizons for applying quantum principles to computing problems by offering an innovative approach to optimization.

Explore how Vector Autoregression (VAR) models can forecast Forex OHLC (Open, High, Low, and Close) time series data. This article covers VAR implementation, model training, and real-time forecasting in MetaTrader 5, helping traders analyze interdependent currency movements and improve their trading strategies.

The Moving-Average-Convergence-Divergence (MACD) oscillator and the On-Balance-Volume (OBV) oscillator are another pair of indicators that could be used in conjunction within an MQL5 Expert Advisor. This pairing, as is practice in these article series, is complementary with the MACD affirming trends while OBV checks volume. As usual, we use the MQL5 wizard to build and test any potential these two may possess.

The article presents an implementation of the Levenberg-Marquardt algorithm for training feedforward neural networks. A comparative analysis of performance with algorithms from the scikit-learn Python library has been conducted. Simpler learning methods, such as gradient descent, gradient descent with momentum, and stochastic gradient descent are preliminarily discussed.

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.

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.

We follow up our last article, where we introduced the indicator pair of the SAR and the RVI, by considering how this indicator pairing could be extended with Machine Learning. SAR and RVI are a trend and momentum 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.