N-BEATS Network-Based Forex EA

N-BEATS Network-Based Forex EA

Implementation of the N-BEATS architecture for Forex trading in MetaTrader 5 with quantile forecasting and adaptive risk management. The architecture is adapted through bilinear normalization and specialized loss functions for financial data. Backtesting on 2025 data shows inability to generate profits, confirming the gap between theoretical achievements and practical trading performance.
Neural network trading EA based on PatchTST

Neural network trading EA based on PatchTST

The article presents the revolutionary architecture of PatchTST, a tailored transformer for financial time series analysis that breaks market data into 16-bar patches for efficient processing. We will discuss the full implementation of a trading robot in MQL5 covering everything from mathematical fundamentals and data structures to a ready-made EA with risk management and continuous learning systems.
Automating Trading Strategies in MQL5 (Part 50): Turtle Soup Liquidity Sweeps

Automating Trading Strategies in MQL5 (Part 50): Turtle Soup Liquidity Sweeps

We build an automated MQL5 program that trades Turtle Soup by fading false breakouts of the N-bar high and low. The article implements liquidity-sweep detection, confirmation closes back inside the level, sweep-depth and extreme-age filters, and an optional reversal-candle body check. It adds configurable dynamic or static stops, two take-profit modes, points-based trailing, and clear chart visuals, providing a ready baseline for backtesting and further customization.
MQL5 Trading Tools (Part 39): Adding a Pinned-Tools Ribbon for Quick Access to Favorite Tools

MQL5 Trading Tools (Part 39): Adding a Pinned-Tools Ribbon for Quick Access to Favorite Tools

We add a pinned-tools ribbon: a floating bar that exposes frequently used tools for one-click access without reopening the sidebar. The article implements the ordered pin set and its API, an anti-aliased pushpin control in the flyout, and the ribbon with offscreen clipping, user-resizable width, and horizontal scrolling. The result is faster activation of favorite tools from a draggable, resizable ribbon on the chart.
Building a Broker-Agnostic Symbol Resolution Layer in MQL5

Building a Broker-Agnostic Symbol Resolution Layer in MQL5

We implement a symbol resolution framework that abstracts broker naming differences in MetaTrader 5. Using a persistent mapping store, layered resolution with validation, a hash-indexed registry, and a cache, it returns selectable symbols with live market data and logs unresolved cases. Practically, you can deploy the same EA across brokers and keep symbol access consistent at low runtime cost.
Engineering a Self-Healing Expert Advisor in MQL5 (Part 5): Real-Time Recovery Dashboard (Final Part)

Engineering a Self-Healing Expert Advisor in MQL5 (Part 5): Real-Time Recovery Dashboard (Final Part)

This article implements a real-time monitoring dashboard for a self-healing MetaTrader 5 Expert Advisor. The dashboard displays the current EA state, virtual stop-loss and take-profit levels, breakeven and trailing status, recovery state, synchronization status, and heartbeat information directly on the chart. By exposing the internal recovery state visually, the Expert Advisor becomes easier to monitor, verify, and troubleshoot while managing active trades.
Building Automated Daily Trading Reports with the SendMail Function

Building Automated Daily Trading Reports with the SendMail Function

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.
Training a nonlinear U-Transformer on the residuals of a linear autoregressive model

Training a nonlinear U-Transformer on the residuals of a linear autoregressive model

The article presents an innovative hybrid system for forecasting exchange rates that combines a linear autoregressive model with a U-Transformer architecture for residual analysis. The system automatically switches between signal sources depending on their quality and includes complete trading logic with averaging/pyramiding strategies. The key advantage of this approach is that the neural network is trained on the residuals of the linear model, which simplifies the task and reduces the risk of overfitting. The implementation is done entirely in MQL5 and is ready for use in real trading with automatic adaptation to changing market conditions.
Automating Trading Strategies in MQL5 (Part 49): The Quasimodo (QM) Reversal Pattern

Automating Trading Strategies in MQL5 (Part 49): The Quasimodo (QM) Reversal Pattern

In this article, we build an automated trading program in MQL5 that detects the Quasimodo reversal pattern from a zig-zag of confirmed swing pivots. We work through swing detection, pattern arming, retrace entries at the QM line, and structural stop placement with risk-based sizing. We also add trade management with breakeven, trailing, and partial closing to handle open positions.
Developing a Neural Network Trading Robot Based on Mamba with Selective State Space Models

Developing a Neural Network Trading Robot Based on Mamba with Selective State Space Models

The article explores the revolutionary Mamba/SSM neural network architecture for financial time series forecasting. We will consider a complete MQL5 implementation of a modern alternative to Transformer with linear complexity O(N) instead of quadratic O(N²). Selective State Space Models, hardware-aware optimizations, patching techniques, and advanced AdamW training methods are covered in detail. Practical test results showing an increase in accuracy from 62% to 71% while reducing training time from 45 to 8 minutes are included. A ready-made trading EA with auto learning and adaptive risk management for MetaTrader 5 is presented.
Engineering a Self-Healing Expert Advisor in MQL5 (Part 4): Trade-State Reconciliation and Safe Mode Recovery

Engineering a Self-Healing Expert Advisor in MQL5 (Part 4): Trade-State Reconciliation and Safe Mode Recovery

This article adds trade-state reconciliation and Safe Mode recovery to a MetaTrader 5 Expert Advisor. The EA continuously validates recovery integrity by comparing the live broker position with the persisted SQLite state and the in-memory runtime state. Detected inconsistencies trigger an automatic transition to Safe Mode, suspending virtual protection, breakeven, and trailing management until the recovery state can be trusted again.
Building an Object-Oriented Session VWAP Engine in MQL5

Building an Object-Oriented Session VWAP Engine in MQL5

This article shows how to implement a session vwap in MQL5 as a reusable include class with a strict daily reset at broker midnight. The engine computes VWAP and volume‑weighted deviation bands only on closed bars and anchors accumulation with MqlDateTime to avoid distortions from missing candles. A companion indicator plots the baseline and bands, while an Expert Advisor reads signals once per bar for consistent, CPU‑efficient execution and reliable testing.
The MQL5 Standard Library Explorer (Part 13): Implementing the Math Solvers Library in Trading

The MQL5 Standard Library Explorer (Part 13): Implementing the Math Solvers Library in Trading

We present a complete workflow for adaptive filtering in MQL5 using the CNlEq Levenberg–Marquardt–like solver. The EA fits a VAMAC model—two EWMAs with an ATR‑based scaling—by supplying residuals and a Jacobian through CNlEq's reverse‑communication loop, with optional numerical or analytical derivatives. Code, setup instructions, and GBPUSD H1 tests show how to replace static thresholds with on‑bar re‑estimation.
MQL5 Trading Tools (Part 38): Adding a Tabbed Settings Window for Editing Object Properties

MQL5 Trading Tools (Part 38): Adding a Tabbed Settings Window for Editing Object Properties

We add a tabbed settings window opened from the ribbon and bound to the selected object. The tabs — Style, Text, Coordinates, and Visibility — are built from the same descriptor system, with scrolling, per-level rows, and shared color/width/style popovers. The article covers layout, rendering, interaction, and inline price/time and numeric editing. You get one place to edit every property with live preview and commit-or-discard on close.
How to Detect and Normalize Chart Objects in MQL5 (Part 3): Alerting and Automated Trading from Manually Drawn Objects

How to Detect and Normalize Chart Objects in MQL5 (Part 3): Alerting and Automated Trading from Manually Drawn Objects

This article extends the chart‑object detector into a modular monitoring and execution layer. It defines objective interaction rules (touch, cross, breakout) for trendlines, Fibonacci levels, channels, rectangles, and pitchforks, then routes events through an interaction detector, alert manager, and optional trade executor. Orders use object geometry for stop‑loss and take‑profit. The result is a reproducible pipeline that converts static drawings into actionable alerts and, if enabled, trades.
Price Action Analysis Toolkit Development (Part 74): Building an MQL5 Expert Advisor from Indicator Buffers

Price Action Analysis Toolkit Development (Part 74): Building an MQL5 Expert Advisor from Indicator Buffers

This article implements an MQL5 Expert Advisor that connects to a weekend gap indicator via iCustom and CopyBuffer, reading six buffers for buy/sell signals and SL/TP. It validates broker stop-distance rules, handles closed-bar confirmation and duplicate-signal control, and executes orders with a configurable magic number. The EA also includes midpoint stop-loss management and a backtesting procedure so you can verify behavior and adapt parameters to your setup.
MQL5 Trading Tools (Part 37): Adding a Per-Object Property-Editing Ribbon to the Canvas Drawing Layer

MQL5 Trading Tools (Part 37): Adding a Per-Object Property-Editing Ribbon to the Canvas Drawing Layer

We add a descriptor-driven property stack and a floating ribbon that binds to the current selection on the drawing layer. The article covers the descriptor list for each tool, the engine get/set API with snapshot-and-restore live preview, and widget renderers for color, opacity, line width, line style, fonts, and level visibility. You get in-place, real-time editing of object appearance via a compact, draggable panel.
Overcoming Accessibility Problems in MQL5 Trading Tools (Part V): Gesture-Based Trading With Computer Vision

Overcoming Accessibility Problems in MQL5 Trading Tools (Part V): Gesture-Based Trading With Computer Vision

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.
Swing Extremes and Pullbacks (Part 4): Dynamic Pullback Depth Using Volatility Models

Swing Extremes and Pullbacks (Part 4): Dynamic Pullback Depth Using Volatility Models

This article replaces binary swing validation with a volatility‑normalized pullback model. Retracement depth is measured as a ratio of the prior impulse and calibrated to a rolling ATR regime, while entries require a minimum quality score and confirmation by structure or liquidity signals. The five‑layer design integrates detection, validation, liquidity mapping, regime‑aware scoring, and execution, helping you filter weak corrections and size stops dynamically to current conditions.
MQL5 Trading Tools (Part 36): Adding Shape and Annotation Tools with In-Place Label Editing to the Canvas Drawing Layer

MQL5 Trading Tools (Part 36): Adding Shape and Annotation Tools with In-Place Label Editing to the Canvas Drawing Layer

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.
Neural Networks in Trading: Actor—Director—Critic

Neural Networks in Trading: Actor—Director—Critic

We invite you to explore the Actor-Director-Critic framework, which combines hierarchical learning and a multi-component architecture for creating adaptive trading strategies. In this article, we take a detailed look at how using the Director to classify the Actor's actions helps to effectively optimize trading decisions and improve the robustness of models in financial market conditions.
Implementing Partial Position Closing in MQL5

Implementing Partial Position Closing in MQL5

This article develops a class for managing partial position closing in MQL5 and then integrates it into an Order Blocks Expert Advisor. It also presents test results comparing the strategy with and without partial position closing, and analyzes the conditions under which this approach can help provide and maximize profit. In conclusion, partial position closing can be highly beneficial in trading strategies, especially those focused on wider price movements.
Quantum Neural Network in MQL5 (Part I): Creating the Include File

Quantum Neural Network in MQL5 (Part I): Creating the Include File

The article presents a new approach to creating trading systems based on quantum principles and artificial intelligence. The author describes the development of a unique neural network that goes beyond classical machine learning by combining quantum mechanics with modern AI architectures.
Step-by-Step Implementation of a Local Stop Loss System in MQL5

Step-by-Step Implementation of a Local Stop Loss System in MQL5

This article shows how to build a local stop-loss system in an MQL5 Expert Advisor that keeps stop levels on the terminal side. It walks through the execution logic, event handlers, inputs, and an OOP design using CTrade, CPositionInfo, CHashMap/CHashSet, and chart objects. You will implement multi-position tracking, draggable stops, visual spacers and labels, plus cleanup and disconnection behavior to create a practical risk-control utility.
MQL5 Trading Tools (Part 35): Adding Channel, Pitchfork, Gann, and Fibonacci Tools to the Canvas Drawing Layer

MQL5 Trading Tools (Part 35): Adding Channel, Pitchfork, Gann, and Fibonacci Tools to the Canvas Drawing Layer

We extend the canvas drawing layer from the previous part with seven new categories of multi-anchor analytical drawing tools, covering three channel variants, three pitchfork variants, three Gann tools, and the six Fibonacci tools. We work through how each tool encodes its geometry on the canvas, how derived handles let users reshape compound shapes coherently, and how shared helpers handle ray clipping, scanline filling, and anti-aliased arc rendering. By the end, we will have a full set of analytical drawing tools that live on the same interactive canvas alongside the basic line tools from the previous part.
Engineering Trading Discipline into Code (Part 7): Automating Equity Protection Through Governance Logic

Engineering Trading Discipline into Code (Part 7): Automating Equity Protection Through Governance Logic

Automated trading systems often focus heavily on signal generation while neglecting the mechanisms required to protect capital during periods of stress. This article presents an Equity Governance Framework in MQL5 that monitors drawdown conditions, evaluates equity pressure, and dynamically controls trading activity through a state-driven risk management model. By combining drawdown analysis, cooldown logic, trade authorization, and execution restrictions, the framework demonstrates how trading discipline can be engineered directly into code using a modular and extensible architecture.
Building an Object-Oriented Z-Score Statistical Arbitrage Engine in MQL5

Building an Object-Oriented Z-Score Statistical Arbitrage Engine in MQL5

This article shows how to implement a production Z-Score engine in MQL5 using an object-oriented include file, the library computes a rolling mean and population standard deviation, exposes a shift parameter for historical queries, and avoids redundant tick work by running on bar close. An Expert Advisor executes rule-based entries at positive/negative sigma thresholds and closes on mean reversion; a custom indicator provides visual verification.