Add a new article
Dynamic mode decomposition applied to univariate time series in MQL5
Dynamic mode decomposition applied to univariate time series in MQL5
Dynamic mode decomposition (DMD) is a technique usually applied to high-dimensional datasets. In this article, we demonstrate the application of DMD on univariate time series, showing its ability to characterize a series as well as make forecasts. In doing so, we will investigate MQL5's built-in implementation of dynamic mode decomposition, paying particular attention to the new matrix method, DynamicModeDecomposition().
Statistical Arbitrage Through Cointegrated Stocks (Part 4): Real-time Model Updating
Statistical Arbitrage Through Cointegrated Stocks (Part 4): Real-time Model Updating
This article describes a simple but comprehensive statistical arbitrage pipeline for trading a basket of cointegrated stocks. It includes a fully functional Python script for data download and storage; correlation, cointegration, and stationarity tests, along with a sample Metatrader 5 Service implementation for database updating, and the respective Expert Advisor. Some design choices are documented here for reference and for helping in the experiment replication.
Market Simulation (Part 01): Cross Orders (I)
Market Simulation (Part 01): Cross Orders (I)
Today we will begin the second stage, where we will look at the market replay/simulation system. First, we will show a possible solution for cross orders. I will show you the solution, but it is not final yet. It will be a possible solution to a problem that we will need to solve in the near future.
Price Action Analysis Toolkit Development (Part 39): Automating BOS and ChoCH Detection in MQL5
Price Action Analysis Toolkit Development (Part 39): Automating BOS and ChoCH Detection in MQL5
This article presents Fractal Reaction System, a compact MQL5 system that converts fractal pivots into actionable market-structure signals. Using closed-bar logic to avoid repainting, the EA detects Change-of-Character (ChoCH) warnings and confirms Breaks-of-Structure (BOS), draws persistent chart objects, and logs/alerts every confirmed event (desktop, mobile and sound). Read on for the algorithm design, implementation notes, testing results and the full EA code so you can compile, test and deploy the detector yourself.
Black Hole Algorithm (BHA)
Black Hole Algorithm (BHA)
The Black Hole Algorithm (BHA) uses the principles of black hole gravity to optimize solutions. In this article, we will look at how BHA attracts the best solutions while avoiding local extremes, and why this algorithm has become a powerful tool for solving complex problems. Learn how simple ideas can lead to impressive results in the world of optimization.
Developing a Replay System (Part 78): New Chart Trade (V)
Developing a Replay System (Part 78): New Chart Trade (V)
In this article, we will look at how to implement part of the receiver code. Here we will implement an Expert Advisor to test and learn how the protocol interaction works. The content presented here is intended solely for educational purposes. Under no circumstances should the application be viewed for any purpose other than to learn and master the concepts presented.
Building a Trading System (Part 3): Determining Minimum Risk Levels for Realistic Profit Targets
Building a Trading System (Part 3): Determining Minimum Risk Levels for Realistic Profit Targets
Every trader's ultimate goal is profitability, which is why many set specific profit targets to achieve within a defined trading period. In this article, we will use Monte Carlo simulations to determine the optimal risk percentage per trade needed to meet trading objectives. The results will help traders assess whether their profit targets are realistic or overly ambitious. Finally, we will discuss which parameters can be adjusted to establish a practical risk percentage per trade that aligns with trading goals.
Multi-module trading robot in Python and MQL5 (Part I): Creating basic architecture and first modules
Multi-module trading robot in Python and MQL5 (Part I): Creating basic architecture and first modules
We are going to develop a modular trading system that combines Python for data analysis with MQL5 for trade execution. Four independent modules monitor different market aspects in parallel: volumes, arbitrage, economics and risks, and use RandomForest with 400 trees for analysis. Particular emphasis is placed on risk management, since even the most advanced trading algorithms are useless without proper risk management.
MetaTrader Meets Google Sheets with Pythonanywhere: A Guide to Secure Data Flow
MetaTrader Meets Google Sheets with Pythonanywhere: A Guide to Secure Data Flow
This article demonstrates a secure way to export MetaTrader data to Google Sheets. Google Sheet is the most valuable solution as it is cloud based and the data saved in there can be accessed anytime and from anywhere. So traders can access trading and related data exported to google sheet and do further analysis for future trading anytime and wherever they are at the moment.
Developing a Replay System (Part 77): New Chart Trade (IV)
Developing a Replay System (Part 77): New Chart Trade (IV)
In this article, we will cover some of the measures and precautions to consider when creating a communication protocol. These are pretty simple and straightforward things, so we won't go into too much detail in this article. But to understand what will happen, you need to understand the content of the article.
From Novice to Expert: Mastering Detailed Trading Reports with Reporting EA
From Novice to Expert: Mastering Detailed Trading Reports with Reporting EA
In this article, we delve into enhancing the details of trading reports and delivering the final document via email in PDF format. This marks a progression from our previous work, as we continue exploring how to harness the power of MQL5 and Python to generate and schedule trading reports in the most convenient and professional formats. Join us in this discussion to learn more about optimizing trading report generation within the MQL5 ecosystem.
Artificial Tribe Algorithm (ATA)
Artificial Tribe Algorithm (ATA)
The article provides a detailed discussion of the key components and innovations of the ATA optimization algorithm, which is an evolutionary method with a unique dual behavior system that adapts depending on the situation. ATA combines individual and social learning while using crossover for explorations and migration to find solutions when stuck in local optima.
Building a Trading System (Part 1): A Quantitative Approach
Building a Trading System (Part 1): A Quantitative Approach
Many traders evaluate strategies based on short-term performance, often abandoning profitable systems too early. Long-term profitability, however, depends on positive expectancy through optimized win rate and risk-reward ratio, along with disciplined position sizing. These principles can be validated using Monte Carlo simulation in Python with back-tested metrics to assess whether a strategy is robust or likely to fail over time.
Statistical Arbitrage Through Cointegrated Stocks (Part 3): Database Setup
Statistical Arbitrage Through Cointegrated Stocks (Part 3): Database Setup
This article presents a sample MQL5 Service implementation for updating a newly created database used as source for data analysis and for trading a basket of cointegrated stocks. The rationale behind the database design is explained in detail and the data dictionary is documented for reference. MQL5 and Python scripts are provided for the database creation, schema initialization, and market data insertion.
MetaTrader 5 Machine Learning Blueprint (Part 2): Labeling Financial Data for Machine Learning
MetaTrader 5 Machine Learning Blueprint (Part 2): Labeling Financial Data for Machine Learning
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.
Price Action Analysis Toolkit Development (Part 37): Sentiment Tilt Meter
Price Action Analysis Toolkit Development (Part 37): Sentiment Tilt Meter
Market sentiment is one of the most overlooked yet powerful forces influencing price movement. While most traders rely on lagging indicators or guesswork, the Sentiment Tilt Meter (STM) EA transforms raw market data into clear, visual guidance, showing whether the market is leaning bullish, bearish, or staying neutral in real-time. This makes it easier to confirm trades, avoid false entries, and time market participation more effectively.
MetaTrader 5 Machine Learning Blueprint (Part 1): Data Leakage and Timestamp Fixes
MetaTrader 5 Machine Learning Blueprint (Part 1): Data Leakage and Timestamp Fixes
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.
Creating 3D bars based on time, price and volume
Creating 3D bars based on time, price and volume
The article dwells on multivariate 3D price charts and their creation. We will also consider how 3D bars predict price reversals, and how Python and MetaTrader 5 allow us to plot these volume bars in real time.
Developing a Replay System (Part 76): New Chart Trade (III)
Developing a Replay System (Part 76): New Chart Trade (III)
In this article, we'll look at how the code of DispatchMessage, missing from the previous article, works. We will laso introduce the topic of the next article. For this reason, it is important to understand how this code works before moving on to the next topic. The content presented here is intended solely for educational purposes. Under no circumstances should the application be viewed for any purpose other than to learn and master the concepts presented.
Self Optimizing Expert Advisors in MQL5 (Part 12): Building Linear Classifiers Using Matrix Factorization
Self Optimizing Expert Advisors in MQL5 (Part 12): Building Linear Classifiers Using Matrix Factorization
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.
Data Science and ML (Part 32): Keeping your AI models updated, Online Learning
Data Science and ML (Part 32): Keeping your AI models updated, Online Learning
In the ever-changing world of trading, adapting to market shifts is not just a choice—it's a necessity. New patterns and trends emerge everyday, making it harder even the most advanced machine learning models to stay effective in the face of evolving conditions. In this article, we’ll explore how to keep your models relevant and responsive to new market data by automatically retraining.
Statistical Arbitrage Through Cointegrated Stocks (Part 2): Expert Advisor, Backtests, and Optimization
Statistical Arbitrage Through Cointegrated Stocks (Part 2): Expert Advisor, Backtests, and Optimization
This article presents a sample Expert Advisor implementation for trading a basket of four Nasdaq stocks. The stocks were initially filtered based on Pearson correlation tests. The filtered group was then tested for cointegration with Johansen tests. Finally, the cointegrated spread was tested for stationarity with the ADF and KPSS tests. Here we will see some notes about this process and the results of the backtests after a small optimization.
Training a multilayer perceptron using the Levenberg-Marquardt algorithm
Training a multilayer perceptron using the Levenberg-Marquardt algorithm
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.
Self Optimizing Expert Advisors in MQL5 (Part 11): A Gentle Introduction to the Fundamentals of Linear Algebra
Self Optimizing Expert Advisors in MQL5 (Part 11): A Gentle Introduction to the Fundamentals of Linear Algebra
In this discussion, we will set the foundation for using powerful linear, algebra tools that are implemented in the MQL5 matrix and vector API. For us to make proficient use of this API, we need to have a firm understanding of the principles in linear algebra that govern intelligent use of these methods. This article aims to get the reader an intuitive level of understanding of some of the most important rules of linear algebra that we, as algorithmic traders in MQL5 need,to get started, taking advantage of this powerful library.
MetaTrader tick info access from MQL5 services to Python application using sockets
MetaTrader tick info access from MQL5 services to Python application using sockets
Sometimes everything is not programmable in the MQL5 language. And even if it is possible to convert existing advanced libraries in MQL5, it would be time-consuming. This article tries to show that we can bypass Windows OS dependency by transporting tick information such as bid, ask and time with MetaTrader services to a Python application using sockets.
ALGLIB library optimization methods (Part II)
ALGLIB library optimization methods (Part II)
In this article, we will continue to study the remaining optimization methods from the ALGLIB library, paying special attention to their testing on complex multidimensional functions. This will allow us not only to evaluate the efficiency of each algorithm, but also to identify their strengths and weaknesses in different conditions.
Expert Advisor based on the universal MLP approximator
Expert Advisor based on the universal MLP approximator
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.
Portfolio optimization in Forex: Synthesis of VaR and Markowitz theory
Portfolio optimization in Forex: Synthesis of VaR and Markowitz theory
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.
Algorithmic trading based on 3D reversal patterns
Algorithmic trading based on 3D reversal patterns
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?
From Novice to Expert: Reporting EA — Setting up the work flow
From Novice to Expert: Reporting EA — Setting up the work flow
Brokerages often provide trading account reports at regular intervals, based on a predefined schedule. These firms, through their API technologies, have access to your account activity and trading history, allowing them to generate performance reports on your behalf. Similarly, the MetaTrader 5 terminal stores detailed records of your trading activity, which can be leveraged using MQL5 to create fully customized reports and define personalized delivery methods.
Developing a Replay System (Part 70): Getting the Time Right (III)
Developing a Replay System (Part 70): Getting the Time Right (III)
In this article, we will look at how to use the CustomBookAdd function correctly and effectively. Despite its apparent simplicity, it has many nuances. For example, it allows you to tell the mouse indicator whether a custom symbol is on auction, being traded, or the market is closed. The content presented here is intended solely for educational purposes. Under no circumstances should the application be viewed for any purpose other than to learn and master the concepts presented.
Utilizing CatBoost Machine Learning model as a Filter for Trend-Following Strategies
Utilizing CatBoost Machine Learning model as a Filter for Trend-Following Strategies
CatBoost is a powerful tree-based machine learning model that specializes in decision-making based on stationary features. Other tree-based models like XGBoost and Random Forest share similar traits in terms of their robustness, ability to handle complex patterns, and interpretability. These models have a wide range of uses, from feature analysis to risk management. In this article, we're going to walk through the procedure of utilizing a trained CatBoost model as a filter for a classic moving average cross trend-following strategy.