MetaTrader 5 Machine Learning Blueprint (Part 26): Process Permutation

MetaTrader 5 Machine Learning Blueprint (Part 26): Process Permutation

We introduce the permutation process for backtest validation: permute bars, rerun the complete development process, and compare the observed Sharpe to the null distribution it produces. Outputs include one-sided p-values, robust z, and quantile confidence intervals, plus a spurious performance curve that quantifies selection versus trial budget. A cache-isolation check prevents false passes. The EURUSD H1 case shows how to set a tolerance and assess whether performance is distinguishable from selection.
A Categorical Hidden Markov Model in MQL5

A Categorical Hidden Markov Model in MQL5

The article provides a detailed examination of the theoretical foundations and practical implementation of the hidden Markov model with categorical emissions (Categorical HMM) in the MQL5 language. Specific examples are used to demonstrate the processes of inference, iterative parameter learning, and online filtering, as well as the methodology for selecting the optimal model architecture based on the AIC/BIC information criteria.
Efficient Volatility Estimation with Garman–Klass: From Theory to a Percentile-Based Trading Tool in MQL5

Efficient Volatility Estimation with Garman–Klass: From Theory to a Percentile-Based Trading Tool in MQL5

This article implements the Garman–Klass volatility estimator as an MQL5 indicator that uses OHLC data for higher statistical efficiency than close-to-close measures. A percentile-based squeeze/expansion detector produces breakout signals, and a companion Expert Advisor executes them via iCustom. Implementation details include series-aware indexing, recursive squeeze-state handling in indicator buffers, and a baseline-on-attach rule for the EA, giving a ready-to-use toolkit for volatility-regime trading.
How to Build a 29-Pair Portfolio with an L1 Filter and VaR-based Allocation of Lots

How to Build a 29-Pair Portfolio with an L1 Filter and VaR-based Allocation of Lots

The article explores the practical application of the L1 Trend Filter for noise reduction and the construction of structural features suitable for live trading. The full workflow is presented: H1 data for 29 instruments from MetaTrader 5, causal filtering, CatBoost with a horizon of three L1 bars, rigorous walk-forward testing, and VaR-based allocation of lots. The reader is provided with a reproducible code pipeline and a portfolio evaluation methodology.
RSI Divergence Grid Expert Advisor with Risk Manager in MQL5

RSI Divergence Grid Expert Advisor with Risk Manager in MQL5

A simple grid trading strategy becomes a resilient system thanks to three components: an entry filter based on RSI divergence, a strict limit on the number of grid levels, and an independent risk manager that monitors equity on every tick and blocks trading when the daily limit or maximum drawdown is reached. The article examines the mathematics behind the classic martingale trap, the implementation of pivot point and RSI divergence detection in MQL5, the complete code for the CRiskManager class with protection against floating losses, and the architecture of the grid itself, with TP based on the weighted average entry price.
Self-Optimizing Expert Advisors in MQL5 (Part 20): Causality Regularization With Time-Lagged Independent Components Analysis (3)

Self-Optimizing Expert Advisors in MQL5 (Part 20): Causality Regularization With Time-Lagged Independent Components Analysis (3)

The article presents a piecewise workflow that forecasts growth in ICA components as surrogate targets and then reconstructs smoothed returns from these forecasts. We analyze dominant-component effects and apply Shapley Additive Explanations to assess feature importance. The approach is implemented end to end, from data preparation to ONNX export and MQL5 integration, providing a practical pipeline for noise reduction and model interpretability.
Markowitz Mean-Variance Optimization for MQL5: A Native Efficient-Frontier Portfolio Builder

Markowitz Mean-Variance Optimization for MQL5: A Native Efficient-Frontier Portfolio Builder

This article shows how to implement a native MQL5 portfolio optimizer for multi-symbol baskets. It derives a covariance matrix from bar log-returns, inverts it via Gauss–Jordan, and solves the global minimum-variance, tangency, and target-return portfolios without external libraries. You will build an EA that rebalances positions long-only with clip-and-renormalize and a read‑only dashboard that tracks drift versus targets, plus learn Strategy Tester setup and common pitfalls.
Testing Random Walk vs Mean Reversion in MQL5: Implementing the Lo-MacKinlay Variance Ratio Test

Testing Random Walk vs Mean Reversion in MQL5: Implementing the Lo-MacKinlay Variance Ratio Test

Implements the Lo–MacKinlay Variance Ratio Test in MQL5 to assess serial dependence via random‑walk variance scaling. Provides a reusable CVarianceRatio class with classical (homoskedasticity) and heteroskedasticity‑robust statistics, plus a script that scans multiple horizons and logs VR and Z‑values. Shows how to embed the test in an Expert Advisor as a statistical gate for mean‑reversion logic.
From Polling to Events: Building a Reactive MQL5 Trading System with Python and Redis Streams

From Polling to Events: Building a Reactive MQL5 Trading System with Python and Redis Streams

An Expert Advisor that takes signals from an external process must know which messages were delivered, which were acknowledged, and which orders reached the broker. This article builds that confirmation protocol on Redis Streams: MQL5 publishes market events, Python suggests trades, and MQL5 alone decides what is executed. Live tests on a demo account show duplicate detection, guard refusals, and dead-lettering; crash recovery is verified with unit tests.
Archimedes Optimization Algorithm (AOA)

Archimedes Optimization Algorithm (AOA)

The article examines the Archimedes Optimization Algorithm — a metaheuristic in which an agent is represented as a physical object with density, volume, and acceleration, and the search itself is reinterpreted as the tendency of bodies submerged in a fluid to reach equilibrium. The balance between exploration and exploitation is not dictated by an external schedule here, but rather stems from the physics of decaying turbulence. We will implement the algorithm in MQL5, test it on a standard test bench, and analyze where this approach works.
Andean Condor Algorithm (ACA)

Andean Condor Algorithm (ACA)

The article implements the Andean Condor Algorithm (ACA) for MQL5 — a compact optimizer with a multiscale intensification operator. A significant improvement in solution quality was observed with a small population: a single adjustment to the settings propels it into the top 45 — and behind this lies a distinctive feature of the algorithm worth knowing about. This resource provides ready-to-use code and practical guidelines for its application.
Entropy Pooling and Scenario Budgets for Expected-Shortfall Sizing

Entropy Pooling and Scenario Budgets for Expected-Shortfall Sizing

Rolling lookback windows implicitly fix a probability vector over past bars. We implement entropy pooling in MQL5 to keep all historical scenarios, reweight them by conditioning on today's volatility under an effective‑scenarios budget, and add views on volatility, tails and correlation. A walk‑forward test, a chart indicator and an ES‑based sizing EA demonstrate how to calibrate risk forecasts and position size to the current regime.
Low-Frequency Quantitative Strategies in MetaTrader 5 (Part 6): A Constant-Dollar Exposure FX Trading System Based on Fixed-Income Interest Rate Yield Differentials

Low-Frequency Quantitative Strategies in MetaTrader 5 (Part 6): A Constant-Dollar Exposure FX Trading System Based on Fixed-Income Interest Rate Yield Differentials

We describe ANANTA, a rules-based FX portfolio model that measures deviations in Interest Rate Swap differentials via moving averages and rebalances constant-dollar exposure across G10 currencies. Designed for intraday operation, it complements or substitutes carry logic without relying on trade volume. Performance is examined from January 2020 to October 2026 for five of the most liquid currencies. Code and free data pipelines are included.
Building a Two-Pole Momentum Oscillator in MQL5

Building a Two-Pole Momentum Oscillator in MQL5

We build a Two‑Pole Momentum Oscillator in MQL5 that measures deviation from a 25‑period SMA, normalizes it by its mean and standard deviation, and smooths the result with two EMA‑style passes. The code defines inputs, buffers, warm‑up and recalculation logic, signal rules, and colorized plots, and derives dynamic targets from the 100‑period average range. It helps detect momentum shifts around the zero line and display price levels tied to recent volatility.
Weibull Reliability Analysis for Strategy Lifespan: Estimating When an EA Is Likely to "Fail"

Weibull Reliability Analysis for Strategy Lifespan: Estimating When an EA Is Likely to "Fail"

We implement a native Weibull maximum-likelihood fit in MQL5 and use it to model strategy wear-out from trade history. Failures are defined as the rolling profit factor dropping below a floor, producing lifetimes in trades. The article wires a survival-based governor into an EA and a companion indicator, so you can estimate conditional survival over the next N trades and apply explicit retirement thresholds with cooldown.
Uncertainty as a Model (Part 6): Multiple Regression and Diagnostics

Uncertainty as a Model (Part 6): Multiple Regression and Diagnostics

A practical introduction to multiple regression with deterministic factors for financial time series. Topics covered include the formulation and matrix form of ordinary least squares (OLS), residual diagnostics, EDA/CDA, R-squared and adjusted R-squared, the F-test, RESET, the Breusch–Pagan test, VIF, and Cook’s distance. Techniques for working with regressors are demonstrated: dummy variables, nonlinear transformations, and interaction terms. Examples involving trends, days of the week, and news help select factors and build models suitable for forecasting.
How to Implement R/S Analysis and the Hurst Indicator in MQL5

How to Implement R/S Analysis and the Hurst Indicator in MQL5

The Hurst exponent indicator for MQL5 is based on R/S analysis using OLS regression in log-log space. The theoretical basis is the findings of Gatheral–Jaisson–Rosenbaum (2014), according to which volatility follows fractional Brownian motion with H ≈ 0.10. The indicator estimates H within a moving window, identifies anti-persistent (H < 0.3), neutral, and trending (H > 0.5) market regimes, colors the line, and triggers an alert upon a regime change, helping you choose a strategy type and manage risk.
Practical Modules from Other Languages in MQL5 (Part 09): MATPLOTLIB (II)

Practical Modules from Other Languages in MQL5 (Part 09): MATPLOTLIB (II)

Learn how to create advanced visualizations in MetaTrader 5 using a Matplotlib-like API from MQL5 while Python handles rendering. We implement key chart types—scatter, bar, horizontal bar, histogram, pie, and hexbin—and show how to control axes, legends, colorbars, and styles. The result is a consistent workflow for exploring trading and financial datasets.
How to Replace a WebSocket EA with TradeMux REST in MetaTrader 5

How to Replace a WebSocket EA with TradeMux REST in MetaTrader 5

The article continues the series on AI Hedge Fund and addresses three limitations of v4: analysts' reputation scores are now stored persistently in SQLite, the EA has been removed from the critical execution path, and signals from the council of fifteen are distributed to multiple brokers via the TradeMux REST API. The logic behind the council and risk management has remained the same: Python retrieves data via the MetaTrader 5 SDK and executes orders directly. The result is resilience to restarts and scalability across multiple terminals.
A Grid Expert Advisor Based on a Cellular Automaton with Online Learning in MQL5 (Part I): Continuous Adaptation of the Trading Model on Each Bar

A Grid Expert Advisor Based on a Cellular Automaton with Online Learning in MQL5 (Part I): Continuous Adaptation of the Trading Model on Each Bar

The article examines the architecture of an Expert Advisor based on a cellular automaton with 10,000 adaptive parameters and an independent binary predictor with a 10-bar prediction horizon. The article demonstrates a three-level online learning process, the evolution of strategies, and validation using a ring buffer and a confusion matrix. The input parameters are reduced to Magic Number, while trading settings are calculated from ATR and five genomes. The EURUSD H1 test yielded an approximate hit rate of 58%, compared to roughly 51% for the fixed MLP.
Building a PDF Creation Library in MQL5 (Part 3): The Byte-Exact Writer

Building a PDF Creation Library in MQL5 (Part 3): The Byte-Exact Writer

The article presents CPdfBuffer and CPdfWriter, a minimal MQL5 pair that derives all offsets from the output buffer instead of hand-maintaining numbers. CPdfWriter records object starts, writes a fixed-width cross-reference table and trailer, and ensures structural consistency. The result passes Part 2's validator, and a ready-to-use script converts arbitrary text to a paginated PDF.
Color Harmony Algorithm (CHA)

Color Harmony Algorithm (CHA)

We take a closer look at the Color Harmony Algorithm (CHA) — a meta-heuristic optimization method based on Munsell's theory of color harmony. We explore the structure of the hue circle, harmony templates, the alternation between the concentration and dispersion phases, and the role of solution memory. From a theoretical framework to a working implementation in MQL5 and unbiased testing on a standard benchmark.
How to Train an MLP Using Markov Chain Features in MQL5

How to Train an MLP Using Markov Chain Features in MQL5

The article describes the two-level MarkovMLPOscillator indicator: a three-state Markov chain uses historical data to construct a transition matrix and generate 15 probabilistic features for each bar, and an MLP is trained on these features to predict price direction at a specified forecast horizon. The article covers feature generation, the validation procedure using a holdout set, and parameter settings. The result is an interpretable oscillator with a color histogram, a smoothed signal, and a display of the current transition matrix.
Market Simulation: First Steps with SQL in MQL5 (III)

Market Simulation: First Steps with SQL in MQL5 (III)

In the previous article, we looked at an example of implementing a class in MQL5 to provide basic support. Its purpose is specifically to allow SQL code to be stored in a separate script file. This way, we won't need to write the same SQL statements as string literals in the MQL5 source code. Although this solution is functional, there are some aspects of it that we can and should improve.
Market Simulation: First Steps with SQL in MQL5 (II)

Market Simulation: First Steps with SQL in MQL5 (II)

Although many people believe that we can easily embed SQL code into other code, this is usually not the case. The reason is that the SQL code is included in the executable as a string. Embedding SQL code as a string, while not a problem for small snippets, can ultimately cause us quite a few headaches.
Bull Optimization Algorithm (BOA)

Bull Optimization Algorithm (BOA)

We present an evolutionary algorithm without a selection operator: the best individual becomes the sole mating partner for the entire population, and classical mutation is replaced by multiplicative mutation with a self-adjusting step size. In this article, we examine three key ideas, implement the algorithm in MQL5 using the C_AO framework, and test it on the standard benchmark suite and in an anti-cheat test — where BOA comes very close to the cutoff for the top 45 but does not make the ranking.
Beyond Squared Returns: Path-Dependent Volatility

Beyond Squared Returns: Path-Dependent Volatility

This article implements a path-dependent volatility model in MQL5 that keeps the sign of returns. The engine uses two-timescale EWMA kernels (four accumulators) to form activity and trend features, with closed-form coefficients and a lightweight kernel search. We provide a calibration workflow and an indicator that plots the decomposition, then test out of sample against EWMA and GARCH on multiple symbols. Results show clear gains on equity indicators and minimal gains on FX.
Behavioural Cloning in a Live Trading System: What Live Experience Can and Cannot Teach

Behavioural Cloning in a Live Trading System: What Live Experience Can and Cannot Teach

This article measures a live-to-train behavioral-cloning loop for an RL trading system across 83 models. Outcome-weighted imitation shifted the policy toward Hold (48% → 82%), with 12 final models not trading at all. Live records were instead used to fit spread and slippage to broker fills, revealing execution costs ~85× higher than in simulation. We describe the loop, the failure mechanism, the calibration, and a protocol to apply.
Fundamentals of Bayesian Inference in Discrete and Continuous Settings: From Theory to Practical Model Implementation

Fundamentals of Bayesian Inference in Discrete and Continuous Settings: From Theory to Practical Model Implementation

The article discusses the fundamentals of Bayesian statistics in both discrete and continuous settings. We will progress from classical Bayes’ theorem and simple examples involving coin flips to conjugate distributions and dynamic Bayesian updating, which enables real-time analysis of market quotes. Using the beta-binomial model as an example, a simple change-point detection indicator has been implemented to help identify shifts in market regimes.
Measuring the Probability of Backtest Overfitting of Your MetaTrader 5 Optimization (Part 1): The CSCV Engine in MQL5

Measuring the Probability of Backtest Overfitting of Your MetaTrader 5 Optimization (Part 1): The CSCV Engine in MQL5

This article implements the Probability of Backtest Overfitting in MQL5 with Combinatorially Symmetric Cross-Validation. It shows how to build the bar-by-bar returns matrix of a parameter grid, aggregate it by blocks and rank the in-sample winner out-of-sample across every split of the history. You get a single probability that this winner ends up in the lower half of the grid out-of-sample, along with the MQL5 code to compute it on your own optimizations.
From Signal to Trade via a Chain of Agents: LangChain Architecture on Top of MQL5

From Signal to Trade via a Chain of Agents: LangChain Architecture on Top of MQL5

The article describes an architecture in which the MQL5 Expert Advisor (EA) handles only data collection and execution, while the logic is moved to a Python server with three LangChain agents: a signal agent, a news agent, and a risk manager. Agents process the WebSocket request sequentially; if any agent rejects it, "hold" is returned. Decisions and actual PnL are stored in SQLite, forming memory and statistics. The reader will receive an interaction diagram, a command protocol, and a feedback approach.
Implementing Session Volume Profile in MQL5

Implementing Session Volume Profile in MQL5

Build a responsive session volume profile indicator in MQL5 from tick data with draggable session bounds and dual anchoring. The article details hash-based bucket aggregation for historical and live ticks, a timer-driven rendering loop with partial updates, automatic or custom bucket sizing, pixel-anchored proportional bars, POC highlighting, and multi‑instance safety—so you can implement, optimize, and run multiple profiles on one chart without UI lag.
Buzzard Optimization Algorithm (BUZOA)

Buzzard Optimization Algorithm (BUZOA)

BUZOA is a population-based metaheuristic algorithm in which each agent randomly selects one of three hunting tactics at each iteration: a narrow search around its personal best, a classic PSO step toward the flock leader, or full teleportation to a random point in the search space. The article examines the implementation of the algorithm in MQL5, identifies a coefficient sign error in the original formulation, and presents benchmark results on a standard test bench.
Online Portfolio Selection: A Provable Regret Bound, and the Cost That Eats It

Online Portfolio Selection: A Provable Regret Bound, and the Cost That Eats It

The article implements Online Portfolio Selection in MQL5: exact simplex projection, four allocators (EG, Universal Portfolio, PAMR, OLMAR), and a BCRP solver on a concave objective. We verify weight paths against the published Python reference and self-check the optimizer. A drift-aware transaction cost model measures turnover and net wealth on a multi-asset basket. Readers get a tested library and evidence on when regret-bounded methods lose to costs.
Using Renko-bar Regression with Error Correction

Using Renko-bar Regression with Error Correction

The article presents a regression-based approach to forecasting Renko bars using CatBoost: the model estimates the logarithmic return of the next bar and the uncertainty of the forecast. We will examine a cascade of residual models with OOF validation using TimeSeriesSplit, shrinkage, and overall early stopping, as well as conditional bias correction. On EURUSD D1, a reduction in OOF-MAE was achieved, along with approximately 65% directional accuracy. A working script for MetaTrader 5 is provided that generates a signal, position size, SL, and TP in brick units.
Real-Time Polynomial Regression: A Causal Savitzky-Golay Implementation for MQL5

Real-Time Polynomial Regression: A Causal Savitzky-Golay Implementation for MQL5

We adapt the Savitzky–Golay filter to a strictly causal, real-time form for MQL5 and derive the fixed coefficients for end-point evaluation. The article provides a full indicator and an Expert Advisor, explains the edge-evaluation noise sensitivity, and implements a multi-bar confirmation safeguard. Backtests on several symbols are shown without cherry-picking. You get ready-to-compile code, parameter guidance, and a reduced-lag alternative to moving averages.
Population-Based Optimization Algorithms: Building a Defense Against Cheaters

Population-Based Optimization Algorithms: Building a Defense Against Cheaters

The algorithms were rerun on the updated functions, and a method was proposed for quickly verifying their "honesty". The composite test combines five different landscapes and eliminates the possibility of gaining an advantage based on the geometry of individual problems, allowing for a quick assessment of the algorithm's actual search capability. A script is provided for preliminary validation of algorithms before they are applied to the optimization of trading strategies.
Benchmark Champions vs. Real-World Optimization Problems

Benchmark Champions vs. Real-World Optimization Problems

We analyze why ratings may be inflated due to the alignment of algorithm trajectories with benchmark diagonals, and we supplement the testing methodology with a requirement to keep the global extremum away from the diagonals. We update Forest and Megacity, and perform RAW verification and calibration using VerifyExtremes.mq5. A drop in HHO and DOAm performance serves as a practical indicator of false leaders.
Hyperdimensional Computing: Learning in One Integer Add, and the Nulls That Judge It

Hyperdimensional Computing: Learning in One Integer Add, and the Nulls That Judge It

A complete Hyperdimensional Computing library for MQL5 implements bind, bundle and permute over 4096‑bit hypervectors, graded level ladders for quantities, an encoder for bars and sequences, and a classifier trained by integer addition. It includes a purged, ordered validation split, online updates without refitting, a market scan with two nulls, and a Python reference that reproduces the MQL5 model bit for bit, so you can validate results and deploy a reproducible indicator and test suite.
The Kalman Filter for Price Smoothing: An Exact Implementation in MQL5

The Kalman Filter for Price Smoothing: An Exact Implementation in MQL5

This article implements the scalar Kalman Filter for price smoothing in MQL5 using the standard local-level model and the exact prediction–update equations. It explains how process and measurement noise (Q, R) shape the Kalman gain, builds two independently configured filters into a fast/slow crossover, and provides a complete indicator and Expert Advisor that trade a stability-confirmed signal via iCustom, giving a reproducible baseline for testing and tuning.