Articles on machine learning in trading
Creating AI-based trading robots: native integration with Python, matrices and vectors, math and statistics libraries and much more.
Find out how to use machine learning in trading. Neurons, perceptrons, convolutional and recurrent networks, predictive models — start with the basics and work your way up to developing your own AI. You will learn how to train and apply neural networks for algorithmic trading in financial markets.
Add a new article
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Category Theory in MQL5 (Part 22): A different look at Moving Averages
In this article we attempt to simplify our illustration of concepts covered in these series by dwelling on just one indicator, the most common and probably the easiest to understand. The moving average. In doing so we consider significance and possible applications of vertical natural transformations.
Developing an MQL5 Reinforcement Learning agent with RestAPI integration (Part 1): How to use RestAPIs in MQL5
In this article we will talk about the importance of APIs (Application Programming Interface) for interaction between different applications and software systems. We will see the role of APIs in simplifying interactions between applications, allowing them to efficiently share data and functionality.
Neural networks made easy (Part 45): Training state exploration skills
Training useful skills without an explicit reward function is one of the main challenges in hierarchical reinforcement learning. Previously, we already got acquainted with two algorithms for solving this problem. But the question of the completeness of environmental research remains open. This article demonstrates a different approach to skill training, the use of which directly depends on the current state of the system.
Self Optimizing Expert Advisors in MQL5 (Part 16): Supervised Linear System Identification
Linear system identifcation may be coupled to learn to correct the error in a supervised learning algorithm. This allows us to build applications that depend on statistical modelling techniques without necessarily inheriting the fragility of the model's restrictive assumptions. Classical supervised learning algorithms have many needs that may be supplemented by pairing these models with a feedback controller that can correct the model to keep up with current market conditions.
Neural networks made easy (Part 51): Behavior-Guided Actor-Critic (BAC)
The last two articles considered the Soft Actor-Critic algorithm, which incorporates entropy regularization into the reward function. This approach balances environmental exploration and model exploitation, but it is only applicable to stochastic models. The current article proposes an alternative approach that is applicable to both stochastic and deterministic models.
Atomic Orbital Search (AOS) algorithm
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.
Population ADAM (Adaptive Moment Estimation)
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.
Neural Networks in Trading: Controlled Segmentation (Final Part)
We continue the work started in the previous article on building the RefMask3D framework using MQL5. This framework is designed to comprehensively study multimodal interaction and feature analysis in a point cloud, followed by target object identification based on a description provided in natural language.
Neural Networks in Trading: Contrastive Pattern Transformer
The Contrastive Transformer is designed to analyze markets both at the level of individual candlesticks and based on entire patterns. This helps improve the quality of market trend modeling. Moreover, the use of contrastive learning to align representations of candlesticks and patterns fosters self-regulation and improves the accuracy of forecasts.
Mining Central Bank Balance Sheet Data to Get a Picture of Global Liquidity
Mining central bank balance sheet data provides a picture of global liquidity in the Forex market and key currencies. We combine data from the Fed, ECB, BOJ and PBoC into a composite index and use machine learning to uncover hidden patterns. This approach turns raw data into real trading signals by combining fundamental and technical analysis.
MQL5 Wizard Techniques you should know (Part 57): Supervised Learning with Moving Average and Stochastic Oscillator
Moving Average and Stochastic Oscillator are very common indicators that some traders may not use a lot because of their lagging nature. In a 3-part ‘miniseries' that considers the 3 main forms of machine learning, we look to see if this bias against these indicators is justified, or they might be holding an edge. We do our examination in wizard assembled Expert Advisors.
Build Self Optimizing Expert Advisors in MQL5 (Part 7): Trading With Multiple Periods At Once
In this series of articles, we have considered multiple different ways of identifying the best period to use our technical indicators with. Today, we shall demonstrate to the reader how they can instead perform the opposite logic, that is to say, instead of picking the single best period to use, we will demonstrate to the reader how to employ all available periods effectively. This approach reduces the amount of data discarded, and offers alternative use cases for machine learning algorithms beyond ordinary price prediction.
Neural Networks Made Easy (Part 86): U-Shaped Transformer
We continue to study timeseries forecasting algorithms. In this article, we will discuss another method: the U-shaped Transformer.
Neural Networks Made Easy (Part 85): Multivariate Time Series Forecasting
In this article, I would like to introduce you to a new complex timeseries forecasting method, which harmoniously combines the advantages of linear models and transformers.
Matrix Factorization: A more practical modeling
You might not have noticed that the matrix modeling was a little strange, since only columns were specified, not rows and columns. This looks very strange when reading the code that performs matrix factorizations. If you were expecting to see the rows and columns listed, you might get confused when trying to factorize. Moreover, this matrix modeling method is not the best. This is because when we model matrices in this way, we encounter some limitations that force us to use other methods or functions that would not be necessary if the modeling were done in a more appropriate way.
Data Science and Machine Learning (Part 16): A Refreshing Look at Decision Trees
Dive into the intricate world of decision trees in the latest installment of our Data Science and Machine Learning series. Tailored for traders seeking strategic insights, this article serves as a comprehensive recap, shedding light on the powerful role decision trees play in the analysis of market trends. Explore the roots and branches of these algorithmic trees, unlocking their potential to enhance your trading decisions. Join us for a refreshing perspective on decision trees and discover how they can be your allies in navigating the complexities of financial markets.
Evolutionary trading algorithm with reinforcement learning and extinction of feeble individuals (ETARE)
In this article, I introduce an innovative trading algorithm that combines evolutionary algorithms with deep reinforcement learning for Forex trading. The algorithm uses the mechanism of extinction of inefficient individuals to optimize the trading strategy.
Neural networks made easy (Part 74): Trajectory prediction with adaptation
This article introduces a fairly effective method of multi-agent trajectory forecasting, which is able to adapt to various environmental conditions.
Neural Networks in Trading: Node-Adaptive Graph Representation with NAFS
We invite you to get acquainted with the NAFS (Node-Adaptive Feature Smoothing) method, which is a non-parametric approach to creating node representations that does not require parameter training. NAFS extracts features of each node given its neighbors and then adaptively combines these features to form a final representation.
Time Evolution Travel Algorithm (TETA)
This is my own algorithm. The article presents the Time Evolution Travel Algorithm (TETA) inspired by the concept of parallel universes and time streams. The basic idea of the algorithm is that, although time travel in the conventional sense is impossible, we can choose a sequence of events that lead to different realities.
Neural networks made easy (Part 71): Goal-Conditioned Predictive Coding (GCPC)
In previous articles, we discussed the Decision Transformer method and several algorithms derived from it. We experimented with different goal setting methods. During the experiments, we worked with various ways of setting goals. However, the model's study of the earlier passed trajectory always remained outside our attention. In this article. I want to introduce you to a method that fills this gap.
Self Optimizing Expert Advisors in MQL5 (Part 8): Multiple Strategy Analysis (2)
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.
Reimagining Classic Strategies (Part X): Can AI Power The MACD?
Join us as we empirically analyzed the MACD indicator, to test if applying AI to a strategy, including the indicator, would yield any improvements in our accuracy on forecasting the EURUSD. We simultaneously assessed if the indicator itself is easier to predict than price, as well as if the indicator's value is predictive of future price levels. We will furnish you with the information you need to decide whether you should consider investing your time into integrating the MACD in your AI trading strategies.
Propensity score in causal inference
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.
Neural Networks in Trading: Hybrid Graph Sequence Models (Final Part)
We continue exploring hybrid graph sequence models (GSM++), which integrate the advantages of different architectures, providing high analysis accuracy and efficient distribution of computing resources. These models effectively identify hidden patterns, reducing the impact of market noise and improving forecasting quality.
MetaTrader 5 Machine Learning Blueprint (Part 11): Kelly Criterion, Prop Firm Integration, and CPCV Dynamic Backtesting
The bet-sizing signal from Part 10 is concurrency-corrected but carries no payoff-ratio adjustment, no response to a hard drawdown budget, and no validation across combinatorial paths. This article covers three additions: a two-stage architecture in which a Kelly payoff multiplier is applied on top of get_signal, preserving the concurrency correction while incorporating win/loss asymmetry; a prop firm integration layer that calibrates the sigmoid w parameter continuously from the remaining drawdown budget under FundedNext Stellar 2-Step rules; and a CPCV backtest framework that simulates a fresh account state across all φ[N, k] paths, producing a Sharpe distribution and a PBO audit.
Population optimization algorithms: Differential Evolution (DE)
In this article, we will consider the algorithm that demonstrates the most controversial results of all those discussed previously - the differential evolution (DE) algorithm.
Neural Networks Made Easy (Part 83): The "Conformer" Spatio-Temporal Continuous Attention Transformer Algorithm
This article introduces the Conformer algorithm originally developed for the purpose of weather forecasting, which in terms of variability and capriciousness can be compared to financial markets. Conformer is a complex method. It combines the advantages of attention models and ordinary differential equations.
Integrate Your Own LLM into EA (Part 5): Develop and Test Trading Strategy with LLMs (II)-LoRA-Tuning
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.
Codex Pipelines, from Python to MQL5, for Indicator Selection: A Multi-Quarter Analysis of the XLF ETF with Machine Learning
We continue our look at how the selection of indicators can be pipelined when facing a ‘none-typical’ MetaTrader asset. MetaTrader 5 is primarily used to trade forex, and that is good given the liquidity on offer, however the case for trading outside of this ‘comfort-zone’, is growing bolder with not just the overnight rise of platforms like Robinhood, but also the relentless pursuit of an edge for most traders. We consider the XLF ETF for this article and also cap our revamped pipeline with a simple MLP.
MQL5 Wizard Techniques you should know (Part 49): Reinforcement Learning with Proximal Policy Optimization
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.
Data Science and ML (Part 43): Hidden Patterns Detection in Indicators Data Using Latent Gaussian Mixture Models (LGMM)
Have you ever looked at the chart and felt that strange sensation… that there’s a pattern hidden just beneath the surface? A secret code that might reveal where prices are headed if only you could crack it? Meet LGMM, the Market’s Hidden Pattern Detector. A machine learning model that helps identify those hidden patterns in the market.
MQL5 Wizard Techniques you should know (Part 43): Reinforcement Learning with SARSA
SARSA, which is an abbreviation for State-Action-Reward-State-Action is another algorithm that can be used when implementing reinforcement learning. So, as we saw with Q-Learning and DQN, we look into how this could be explored and implemented as an independent model rather than just a training mechanism, in wizard assembled Expert Advisors.
Category Theory in MQL5 (Part 4): Spans, Experiments, and Compositions
Category Theory is a diverse and expanding branch of Mathematics which as of yet is relatively uncovered in the MQL5 community. These series of articles look to introduce and examine some of its concepts with the overall goal of establishing an open library that provides insight while hopefully furthering the use of this remarkable field in Traders' strategy development.
Neural networks made easy (Part 42): Model procrastination, reasons and solutions
In the context of reinforcement learning, model procrastination can be caused by several reasons. The article considers some of the possible causes of model procrastination and methods for overcoming them.
Neural Networks Made Easy (Part 95): Reducing Memory Consumption in Transformer Models
Transformer architecture-based models demonstrate high efficiency, but their use is complicated by high resource costs both at the training stage and during operation. In this article, I propose to get acquainted with algorithms that allow to reduce memory usage of such models.
Fibonacci in Forex (Part I): Examining the Price-Time Relationship
How does the market observe Fibonacci-based relationships? This sequence, where each subsequent number is equal to the sum of the two previous ones (1, 1, 2, 3, 5, 8, 13, 21...), not only describes the growth of the rabbit population. We will consider the Pythagorean hypothesis that everything in the world is subject to certain relationships of numbers...
Neural Networks in Trading: A Complex Trajectory Prediction Method (Traj-LLM)
In this article, I would like to introduce you to an interesting trajectory prediction method developed to solve problems in the field of autonomous vehicle movements. The authors of the method combined the best elements of various architectural solutions.
Neural Network in Practice: Sketching a Neuron
In this article we will build a basic neuron. And although it looks simple, and many may consider this code completely trivial and meaningless, I want you to have fun studying this simple sketch of a neuron. Don't be afraid to modify the code, understanding it fully is the goal.
Unified Validation Pipeline Against Backtest Overfitting
This article explains why standard walkforward and k-fold CV inflate results on financial data, then shows how to fix it. V-in-V enforces strict data partitions and anchored walkforward across windows, CPCV purges and embargoes leakage while aggregating path-wise performance, and CSCV measures the Probability of Backtest Overfitting. Practitioners gain a coherent framework to assess regime robustness and selection reliability.