Covariance Matrix Adaptation Evolution Strategy (CMA-ES)
Covariance Matrix Adaptation Evolution Strategy (CMA-ES)
The article explores one of the most interesting non-gradient optimization algorithms, which learns to understand the geometry of the objective function. We will focus on the classical implementation of CMA-ES with a slight modification - replacing the normal distribution with the power one. We will thoroughly examine the math behind the algorithm, as well as practical implementation, and check where CMA-ES is unbeatable and where it should be avoided.
Modular Indicator Architecture in MQL5 (Part 1): Stop Copy-Pasting and Start Writing Scalable, Reusable Code
Modular Indicator Architecture in MQL5 (Part 1): Stop Copy-Pasting and Start Writing Scalable, Reusable Code
This article develops an object-oriented framework for MQL5 indicators by evolving a primitive example into reusable modules. It formalizes partial buffer recalculation in OnCalculate, moves logic into header-based classes (CAppliedPrice, CSma), and introduces CSubIndiBase, CIndicatorBase, and a registry to centralize requirements. You get portable components, isolated inputs, and clean buffers with minimal boilerplate, making new indicators faster to assemble and easier to maintain.
Detecting and Classifying Fractal Patterns Using Machine Learning
Detecting and Classifying Fractal Patterns Using Machine Learning
In this article, we will touch upon the intriguing topic of fractal analysis and market forecasting using machine learning. These are just the first steps towards exploring the diverse fractal structures that form on financial price charts. We will use the correlation to find patterns and the CatBoost algorithm to classify these patterns.
Position Management: Scaling Into Winners With A Falling-Risk Pyramid
Position Management: Scaling Into Winners With A Falling-Risk Pyramid
We introduce CPyramidBridge, a thin MQL5 layer that maps bet-sizing results to CPyramidEngine. The bridge applies probability to initial lot sizing, enforces a capacity-aware entry gate, promotes add-ons from dynamic divergence, adapts the trailing stop to reserve estimates, and syncs signals on close, allowing an Expert Advisor to convert model confidence and concurrency into a structured, decreasing-risk pyramid.
Custom Debugging and Profiling Tools for MQL5 Development (Part II): Profiling EAs and Testing Trading Logic
Custom Debugging and Profiling Tools for MQL5 Development (Part II): Profiling EAs and Testing Trading Logic
We build a compact profiler that records calls, min/max/average times, and slow-call counts to CSV, and a simple test runner that writes deterministic pass/fail reports. The article explains where to place measurements in an EA, how to sample ticks, and how to keep pure calculations testable. Running the script first and the profiling EA second provides repeatable evidence for regression analysis.
Integrating MQL5 with Data Processing Packages (Part 9): Entropy-Based Adaptive Volatility
Integrating MQL5 with Data Processing Packages (Part 9): Entropy-Based Adaptive Volatility
This work presents an end-to-end pipeline: collect MetaTrader 5 data, engineer entropy/volatility/trend features, train a PyTorch classifier, and expose predictions through a Flask API. An MQL5 EA posts rolling prices each tick, receives probability and regime, and applies adaptive position sizing and stop distances. The result is a clear recipe for integrating ML inference with MetaTrader 5.
Dolphin Echolocation Algorithm (DEA)
Dolphin Echolocation Algorithm (DEA)
In this article, we take a closer look at the DEA algorithm, a metaheuristic optimization method inspired by dolphins' unique ability to find prey using echolocation. From mathematical foundations to practical implementation in MQL5, from analysis to comparison with classical algorithms, we will examine in detail why this relatively new method deserves a place in the arsenal of researchers facing optimization problems.
MetaTrader 5 Machine Learning Blueprint (Part 17): CPCV Backtesting — From Python Model to Tick-Level Evidence
MetaTrader 5 Machine Learning Blueprint (Part 17): CPCV Backtesting — From Python Model to Tick-Level Evidence
We bridge Python-native artifacts to MQL5 for tick-accurate CPCV backtesting. The export script converts the ONNX model, calibrator, feature spec, and path masks to flat files, while the expert advisor rebuilds features, performs ONNX inference with calibration, and trades on real ticks. The Strategy Tester runs each combinatorial path, and Python aggregates per-path equities into a path Sharpe distribution to assess robustness after spread, slippage, and commission.
Interactive Supply and Demand Zone Manager in MQL5: From Manual to Automated Lifecycle
Interactive Supply and Demand Zone Manager in MQL5: From Manual to Automated Lifecycle
Replace static drawings with automated, stateful zones controlled by a CZone wrapper. The system synchronizes user rectangles, sizes zones by ATR, validates breakouts using consecutive closes, applies ghost/deactivation rules, merges nearby structures by a 1.5×ATR threshold, and projects edges forward. Traders gain durable levels that update themselves and reduce repetitive chart management.
Backtracking Search Algorithm (BSA)
Backtracking Search Algorithm (BSA)
What if an optimization algorithm could remember its past journeys and use that memory to find better solutions? BSA does just that – balancing exploration with revisiting the tried and true. In this article, we reveal the secrets of the algorithm. A simple idea, minimum parameters and a stable result.
Building AI-Powered Trading Systems in MQL5 (Part 9): Creating an AI Signal Dispatcher
Building AI-Powered Trading Systems in MQL5 (Part 9): Creating an AI Signal Dispatcher
We turn the MQL5 AI trading assistant into a dispatch-driven system that routes seven trading actions through a single central dispatcher. A line-based key-value protocol constrains AI output, while each action maps to market or pending orders and instrument-aware stop levels. A canvas-based UI with a custom prompt editor and pixel-accurate text fitting makes signals consistent, auditable, and ready to render on the chart
Trading with the MQL5 Economic Calendar (Part 11): Modular Canvas News Dashboard
Trading with the MQL5 Economic Calendar (Part 11): Modular Canvas News Dashboard
We rebuild the MQL5 Economic Calendar dashboard from a monolithic object-based panel into a modular canvas-based system split across four files. The update adds a dual light and dark theme, collapsible day groups, a resizable layout with pixel-based scrolling, revised value markers, and a live countdown with toast notifications. A candidate event cache and a fast-path timer that repaints only changed cells improve responsiveness and make the codebase easier to extend.
Trading with the MQL5 Economic Calendar (Part 12): SQLite Storage and Deduplication
Trading with the MQL5 Economic Calendar (Part 12): SQLite Storage and Deduplication
In this article, we replace the embedded CSV snapshot with a SQLite layer that persists calendar events and triggered trade IDs across restarts. The database lives in the common terminal folder and is shared by live charts and the strategy tester, so both modes read the same data without recompiling. An on-demand downloader with a canvas progress bar fetches history from the calendar API and stores it for offline reuse.