Articles with examples of trading robots developed in MQL5

Kohonen's self-organizing maps transform the chaos of market data into an ordered two-dimensional map, where similar patterns are grouped together. The article demonstrates a complete implementation of a SOM in an MQL5 Expert Advisor with 400 neurons and continuous learning. We break down the Best Matching Unit search algorithm, weight updates using a Gaussian neighborhood function, integration with quantum effects, and the generation of trading signals. The code is open-source, the math is clear, and the results are verifiable.

We continue to work on implementing the CATCH framework, which combines the Fourier transform and frequency patching mechanisms, ensuring accurate detection of market anomalies. In this article, we complete the implementation of our own vision of the proposed approaches and test the new models on real historical data.

Mantis is a versatile tool for in-depth time series analysis that can be flexibly scaled to accommodate any financial scenario. Learn how a combination of patching, local convolutions, and cross-attention enables a highly accurate interpretation of market patterns.

We build an MQL5 Expert Advisor that emails a structured daily trading report. The article shows how to configure SMTP in MetaTrader 5, collect and filter closed trades for the previous day, compute totals for profit, wins, losses, and trade count, and assemble account details into the subject and body. You also schedule one send per day and prevent duplicates using daily candle detection.

We build a session-based reversal program in MQL5 using the Bread and Butter Judas Swing model. It derives a higher-timeframe daily bias, defines New York kill zones, maps each session's premium and discount from the live range, and requires a sweep before a market structure shift confirms entry. Readers get a ready approach to arm setups only during active sessions and execute in the bias direction with clear, testable rules.

We add eight shape tools and nine annotation tools to the canvas and implement a full in-place label-editing system. The article walks through geometry, AA rendering, shared word-wrap and supersampled text helpers, and the caret-driven state machine for typing, navigation, and selection. This yields a complete, consistent annotation toolkit with editable labels that plugs into the prior interaction pipeline.

We describe an MQL5 framework that aligns entries with session rhythms and scheduled clock events. A script identifies the broker's time zone and DST by detecting NFP spikes on EURUSD and matching them to EU/US/AU transition dates, producing EA‑ready settings. Session-to-broker time conversion and 15-minute marks constrain execution. A multi‑timeframe AMA signal aggregates trends for strategy selection and optimization.

This article shows how to build a hands-free trading workflow for MetaTrader 5 by translating webcam-tracked hand gestures into MQL5 trade commands. We cover the architecture (MediaPipe/OpenCV in Python plus an MQL5 EA), gesture-to-action mapping, and interprocess communication via Global Variables or HTTP polling. You will implement the EA, execute BUY/SELL/CLOSE actions, and validate latency and reliability under real‑time conditions.

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.

Building on Part 2, the implementation introduces restart-aware breakeven and trailing-stop systems for MetaTrader 5. The EA persists the state, such as breakeven activation, last trailing price, and virtual SL in SQLite, then restores them on startup. This preserves dynamic protection flow and prevents lost progress after terminal interruptions.

The Mantis framework transforms complex time series into informative tokens and serves as a reliable foundation for an intelligent trading agent capable of operating in real time.

This article introduces a modular Fair Value Gap (FVG) detection engine for MQL5 packaged as a reusable include class, it evaluates imbalance zones on closed bars, applies a Simple True Range average filter to eliminate low-volatility noise, and supports wick-touch and close-through mitigation. A companion diagnostic indicator plots active gaps, and an Expert Advisor template demonstrates automated pullback entries with new-bar execution controls.

In this article, we build the core of the TimeFound intelligent model step by step, adapting it to real-world time series forecasting tasks. If you are interested in the practical implementation of neural network patching algorithms in MQL5, you have come to the right place.

We continue our acquaintance with the Mamba4Cast framework. Today, we will delve into the practical implementation of the proposed approaches. Mamba4Cast was designed not for lengthy warm-up on every new time series, but for immediate deployment. Thanks to the concept of Zero-Shot Forecasting, the model can produce high-quality forecasts on real-world data without additional training or hyperparameter tuning.

We implement a Hierarchical Risk Parity allocator in MQL5 as a single class, validate each stage against an independent Python reference, and package it in a rebalancing Expert Advisor. The pipeline covers returns, covariance/correlation, clustering, quasi-diagonalization, and recursive bisection, and contrasts HRP with Markowitz on stressed data. You finish with a verified allocator and an EA ready for basket-level testing.

Build a level-2 path-signature engine in pure MQL5 to read the lead-lag ordering between two data streams without choosing a lag and without a linear model. The article delivers a reusable library, an indicator that plots the Levy‑area oscillator, and a simple rule‑based Expert Advisor. Code is cross‑checked against closed‑form cases, and the components are ready to plug into your projects.

The article focuses on the practical implementation of the TimeFound model for time series forecasting. The key stages of implementing the framework's main approaches using MQL5 are examined.