Articles on trading system automation in MQL5

The article proposes the method of creating bots using machine learning.

In this article, we will consider conformal predictions and the MAPIE library that implements them. This approach is one of the most modern ones in machine learning and allows us to focus on risk management for existing diverse machine learning models. Conformal predictions, by themselves, are not a way to find patterns in data. They only determine the degree of confidence of existing models in predicting specific examples and allow filtering for reliable predictions.

Explore whether financial markets are truly random by recreating Larry Williams’ market behavior experiments using MQL5. This article demonstrates how simple price-action tests can reveal statistical market biases using a custom Expert Advisor.

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.

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.

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.

In this article, we develop an MQL5 First Run User Setup Wizard for Expert Advisors, featuring a scrollable guide with an interactive dashboard, dynamic text formatting, and visual controls like buttons and a checkbox allowing users to navigate instructions and configure trading parameters efficiently. Users of the program get to have insight of what the program is all about and what to do on the first run, more like an orientation model.

In this article we will continue the simulator development stage. this time we will see how to effectively create a RANDOM WALK type movement. This type of movement is very intriguing because it forms the basis of everything that happens in the capital market. In addition, we will begin to understand some concepts that are fundamental to those conducting market analysis.

In this article, we enhance the gauge-based indicator in MQL5 to support multiple oscillators, allowing user selection through an enumeration for single or combined displays. We introduce sector and round gauge styles via derived classes from a base gauge framework, improving case rendering with arcs, lines, and polygons for a more refined visual appearance.

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.

Today, we use the MQL5 Standard Library to build custom signal classes and let the MQL5 Wizard assemble a professional Expert Advisor for us. This approach simplifies development so that even beginner programmers can create robust EAs without in-depth coding knowledge, focusing instead on tuning inputs and optimizing performance. Join this discussion as we explore the process step by step.

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.

This article applies Depth-First Search to market structure by modeling swing highs and lows as graph nodes and tracking one structural path as deeply as conditions remain valid. When a key swing is broken, the algorithm backtracks and explores an alternative branch. Readers gain a practical framework to formalize structural bias and test whether the current path aligns with targets like liquidity pools or supply and demand zones.

The article describes a complete pipeline that uses data analysis for finding low-frequency lead/lag trading opportunities. It goes into building a cross-correlation-based Lead/Lag analyser step-by-step, with special attention to the most common errors beginners may commit while developing cross-asset diffusion queries. After screening dozens of cointegrated and correlated pairs, a trading candidate pair is chosen, and its tradeability is evaluated in a pure SQL backtest. Once it is qualified, the strategy is backtested on the MetaTester for parameter optimization. The Expert Advisor with respective backtest settings and optimization inputs is provided, along with Python and SQL scripts.

Moving Averages are a very common indicator that are used and understood by most Traders. We explore possible use cases that may not be so common within MQL5 Wizard assembled Expert Advisors.

In this article, we explore a powerful MQL5 tool that let's you test any price level you desire with just one click. Simply enter your chosen level and press analyze, the EA instantly scans historical data, highlights every touch and breakout on the chart, and displays statistics in a clean, organized dashboard. You'll see exactly how often price respected or broke through your level, and whether it behaved more like support or resistance. Continue reading to explore the detailed procedure.

Join us as we discuss how you can use AI to optimize your position sizing and order quantities to maximize the returns of your portfolio. We will showcase how to algorithmically identify an optimal portfolio and tailor your portfolio to your returns expectations or risk tolerance levels. In this discussion, we will use the SciPy library and the MQL5 language to create an optimal and diversified portfolio using all the data we have.

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.

In this article, we implement filters in the MQL5 Economic Calendar dashboard to refine news event displays by currency, importance, and time. We first establish filter criteria for each category and then integrate these into the dashboard to display only relevant events. Finally, we ensure each filter dynamically updates to provide traders with focused, real-time economic insights.

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.

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.

The article describes and codes MR Swing in MQL5, a mean‑reversion swing approach that combines a 200‑day hysteresis channel with Value Charts, DVO, and SVAPO. We document entry/exit rules for bull and bear regimes and show five‑year backtests on six high‑liquidity Nasdaq stocks. The complete EA code and backtest configurations are provided for reproducibility.

The article examines three key obstacles to integrating LLMs with MetaTrader 5: the lack of direct access, strict rate limits, and API key security given the architectural limitations of MQL5. A configuration is proposed that uses a local Python server as a bridge between the Expert Advisor and OpenRouter. The article covers WebSocket and fallback to TCP, storing the key on the server, batch processing of multiple symbols, and constructing a technical prompt. Readers get a ready-made architecture that reduces latency and costs.

The article describes the development of a multi-agent machine learning system for algorithmic trading on MetaTrader 5 based on reinforcement learning. The system has a three-tier architecture: memory neurons store experience, agents make independent decisions, and the collective mind combines them through weighted voting. The system is continuously improved through Q-learning, pruning of ineffective neurons, and evolutionary reduction of exploration.

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.

The Triple Exponential Moving Average Oscillator (TRIX) and the Williams Percentage Range Oscillator are another pair of indicators that could be used in conjunction within an MQL5 Expert Advisor. This indicator pair, like those we’ve covered recently, is also complementary given that TRIX defines the trend while Williams Percent Range affirms support and Resistance levels. As always, we use the MQL5 wizard to prototype any potential these two may have.

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.

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.

This article introduces a fairly effective method of multi-agent trajectory forecasting, which is able to adapt to various environmental conditions.

We revamp our earlier articles on testing trade setups with the MQL5 Wizard by putting a bit more emphasis on input data quality, cleaning, and handling. In the earlier articles we had looked at a lot of custom signal classes, usable by the wizard, so we now shift our focus to a custom trailing class, given that exiting is also a very important part in any trading system. Our broad theme for this particular piece data-efficiency and the O(1) range-query; the core ‘tech’ is MQL5, SQLite, Python-Polars; the Algorithm is the Sparse-Table while we will seek validation from the ATR Indicator.

This Expert Advisor, named SMOC (likely standing for Stochastic Model Optimal Control), is a simple example of an advanced algorithmic trading system for MetaTrader 5. It uses a combination of technical indicators, model predictive control, and dynamic risk management to make trading decisions. The EA incorporates adaptive parameters, volatility-based position sizing, and trend analysis to optimize its performance across varying market conditions.