Add a new article
MetaTrader 5 Machine Learning Blueprint (Part 9): Integrating Bayesian HPO into the Production Pipeline
MetaTrader 5 Machine Learning Blueprint (Part 9): Integrating Bayesian HPO into the Production Pipeline
​This article integrates the Optuna hyperparameter optimization (HPO) backend into a unified ModelDevelopmentPipeline. It adds joint tuning of model hyperparameters and sample-weight schemes, early pruning with Hyperband, and crash-resistant SQLite study storage. The pipeline auto-detects primary vs. secondary models, prepends a fitted column-dropping preprocessor for safe inference, supports sequential bootstrapping, generates an Optuna report, and includes bid/ask and LearnedStrategy links. Readers get faster, resumable runs and deployable, self-contained models.
Creating Custom Indicators in MQL5 (Part 10): Enhancing the Footprint Chart with Per-Bar Volume Sentiment Information Box
Creating Custom Indicators in MQL5 (Part 10): Enhancing the Footprint Chart with Per-Bar Volume Sentiment Information Box
The article enhances an MQL5 footprint indicator with a compact box above each candle that summarizes net delta, total volume, and buy/sell percentages. We implement supersampled anti‑aliased rendering, rounded corners via arc and quadrilateral rasterization, and per‑pixel alpha compositing. Supporting utilities include ARGB conversion, scanline fills, and box‑filter downsampling. The box delivers fast sentiment reads that stay legible across zoom levels.
Neural Networks in Trading: Adaptive Detection of Market Anomalies (DADA)
Neural Networks in Trading: Adaptive Detection of Market Anomalies (DADA)
We invite you to get acquainted with the DADA framework, which is an innovative method for detecting anomalies in time series. It helps distinguish random fluctuations from suspicious deviations. Unlike traditional methods, DADA is flexible and adapts to different data. Instead of a fixed compression level, it uses several options and chooses the most appropriate one for each case.
Coral Reefs Optimization (CRO)
Coral Reefs Optimization (CRO)
The article presents a comprehensive analysis of the Coral Reef Optimization (CRO) algorithm, a metaheuristic method inspired by the biological processes of coral reef formation and development. The algorithm models key aspects of coral evolution: broadcast spawning, brooding, larval settlement, asexual reproduction, and competition for limited reef space. Particular attention is paid to the improved version of the algorithm.
From Novice to Expert: Adaptive Risk Management for Liquidity Strategies
From Novice to Expert: Adaptive Risk Management for Liquidity Strategies
In this article, we explore practical and robust risk management techniques specifically tailored for liquidity-based trading. You will learn how to protect positions during retests, handle false breakouts with confidence, and identify signs of potential level manipulation. By the end, you will have built an adaptive Expert Advisor capable of managing zone flips and executing strategic pending orders with integrated risk control.
Price Action Analysis Toolkit Development (Part 65): Building an MQL5 System to Monitor and Analyze Manually Drawn Fibonacci Levels
Price Action Analysis Toolkit Development (Part 65): Building an MQL5 System to Monitor and Analyze Manually Drawn Fibonacci Levels
The Fibonacci retracement tool is an essential component of price action analysis, providing critical levels for potential market reactions. However, its effectiveness is often limited by the need for continuous human monitoring, which can lead to missed setups. In this part of our series, we introduce a tool that synchronizes and actively monitors manually drawn Fibonacci levels using MQL5, combining discretionary insight with automated oversight.
Neuro-Structural Trading Engine — NSTE (Part II): Jardine's Gate Six-Gate Quantum Filter
Neuro-Structural Trading Engine — NSTE (Part II): Jardine's Gate Six-Gate Quantum Filter
This article introduces Jardine's Gate, a six-gate orthogonal signal filter for MetaTrader 5 that validates LSTM predictions across entropy, expert interference, confidence, regime-adjusted probability, trend direction, and consecutive-loss kill switch dimensions. Out of 43,200 raw signals per month, only 127 pass all six gates. Readers get the complete QuantumEdgeFilter MQL5 class, threshold calibration logic, and gate performance analytics.
Trend Criteria. Conclusion
Trend Criteria. Conclusion
In this article, we will consider the specifics of applying some trend criteria in practice. We will also try to develop several new criteria. The focus will be on the efficiency of applying these criteria to market data analysis and trading.
MQL5 Trading Tools (Part 26): Integrating Frequency Binning, Entropy, and Chi-Square in Visual Analyzer
MQL5 Trading Tools (Part 26): Integrating Frequency Binning, Entropy, and Chi-Square in Visual Analyzer
In this article, we develop a frequency analysis tool in MQL5 that bins price data into histograms, computes entropy for information content, and applies chi-square tests for distribution goodness-of-fit, with interactive logs and statistical panels for market insights. We integrate per-bar or per-tick computation modes, supersampled rendering for smooth visuals, and draggable/resizable canvases with auto-scrolling logs to enhance usability in trading analysis.
Pair Trading: Algorithmic Trading with Auto Optimization Based on Z-Score Differences
Pair Trading: Algorithmic Trading with Auto Optimization Based on Z-Score Differences
In this article, we will explore what pair trading is and how correlation trading works. We will also create an EA for automating pair trading and add the ability to automatically optimize this trading algorithm based on historical data. In addition, as part of the project, we will learn how to calculate the differences between two pairs using the z-score.
Market Simulation (Part 18): First Steps in SQL (I)
Market Simulation (Part 18): First Steps in SQL (I)
It doesn't matter which SQL program we use: MySQL, SQL Server, SQLite, OpenSQL, or another. They all have something in common, and that common element is the SQL language. Even if we do not intend to use WorkBench, we can manipulate or work with the database directly in MetaEditor or through MQL5 to perform actions in MetaTrader 5, but to do so, you will need knowledge of SQL. So here, we will learn at least the basics.
MetaTrader 5 Machine Learning Blueprint (Part 10): Bet Sizing for Financial Machine Learning
MetaTrader 5 Machine Learning Blueprint (Part 10): Bet Sizing for Financial Machine Learning
Fixed fractions and raw probabilities misallocate risk under overlapping labels and induce overtrading. This article delivers four AFML-compliant sizers: probability-based (z-score → CDF, active-bet averaging, discretization), forecast-price (sigmoid/power with w calibration and limit price), budget-constrained (direction-only), and reserve (mixture-CDF via EF3M). You get a signed, bounded position series with documented conditions of use.
Swing Extremes and Pullbacks in MQL5 (Part 3): Defining Structural Validity Beyond Simple Highs/Lows
Swing Extremes and Pullbacks in MQL5 (Part 3): Defining Structural Validity Beyond Simple Highs/Lows
This article presents an MQL5 Expert Advisor that upgrades raw swing detection to a rule-based Structural Validation Engine. Swings are confirmed by a break of structure, displacement, liquidity sweeps, or time-based respect, then linked to a liquidity map and a structural state machine. The result is context-aware entries and stops anchored to validated levels, helping filter noise and systematize execution.
Market Simulation (Part 19): First Steps in SQL (II)
Market Simulation (Part 19): First Steps in SQL (II)
As we explained in the first article about SQL, there is no point in spending time programming procedures to do what is already built into SQL. However, without knowing the basics, you won’t be able to do anything with SQL or take full advantage of everything this tool offers. Therefore, in this article, we will look at how to perform basic tasks in databases.