Part 5 moves risk control from single trades to a basket-level framework. The EA aggregates its own positions, computes volume‑weighted entry, floating P/L including swap, and used margin, then enforces limits on combined loss, margin, position count, and time underwater, while logging maximum adverse excursion. A companion mean‑reversion EA demonstrates target‑based sizing and caps on implied risk that remains hidden when trades are evaluated in isolation.
The article will show you how Mamba4Cast turns theory into a working trading algorithm and lays the groundwork for your own experiments. Do not miss this opportunity to gain a full range of knowledge and inspiration for developing your own strategy.
We build a robust MQL5 detector for double tops and double bottoms that first confirms the H4 trend, then validates six conditions (point equality, neckline placement, ordering, width, height, and ATR‑based tolerances). The neckline break is timed on the chart's timeframe, and a three-state machine ensures each pattern trades once. The measured‑move target translates structure into clear exits.
In this article, we begin our exploration of the SSCNN framework — a modern architectural solution for time series analysis that combines accuracy, a structured design, and high computational efficiency. We will systematically examine its theoretical aspects, highlight the key differences from its predecessors, and begin the practical implementation of its basic components in the MQL5 environment.
We examine how a Hidden Markov Model (HMM) estimates latent market regimes while basing on observable price and indicator sequences. This is done by estimating the probability of state transitions. A Gated Recurrent Unit (GRU) network models time dependencies and keeps important information over several observations. In an Expert Advisor, HMM-based regime probabilities, can be merged with GRU-based sequence learning to better classify increments in accumulation, distribution, and momentum prior to their showing up in regular price confirmations.
We introduce a Partial Information Decomposition library for MQL5 that decomposes two sources about a target into four atoms: unique to each, shared, and synergy. The implementation uses quantile binning, tabulated logarithms, and a maximum-entropy fit (for I_ccs), and it pairs results with a block-permutation null because atoms sit above zero on finite samples. Use it to screen indicator pairs and judge significance, including family-wise correction.
The article provides a detailed explanation of the SCNN architecture and one way to implement it using MQL5. We will show how time series decomposition can be combined with neural network methods and attention mechanisms.
This part implements risk-based position sizing for the EA. Lot size is derived from account balance, a chosen risk percent, and ATR-based stop distance, then confined and rounded to the broker's volume rules and minimum stop levels. An optional drawdown-aware layer reduces risk during equity declines. Readers get a reproducible sizing function that keeps per-trade risk consistent and orders acceptable to the server.
We invite you to explore the next stage in implementing the SCNN framework, which combines flexibility and interpretability, allowing structural components of a time series to be identified precisely. The article provides a detailed explanation of the mechanisms of adaptive normalization and attention, which ensure the model's resilience to changing market conditions.
This article develops a market‑structure‑driven intraday breakout system based on Bill Williams fractals. We define session bounds, derive volatility‑scaled stops, use fixed risk and take‑profit multipliers, and limit trades to one per direction. An MQL5 Expert Advisor, visualization and statistics, tick-level backtests, an ORB comparison, and a cross-asset forward test provide a complete, replicable workflow.
We invite you to explore the innovative SCNN framework, which takes time series analysis to a new level by clearly separating data into long-term, seasonal, short-term, and residual components. This approach significantly improves forecasting accuracy by allowing the model to adapt to complex and changing market dynamics.
This article presents a complete RL trading pipeline for XAUUSD: a supervised signal baseline with triple-barrier labels, PPO training, purged walk-forward validation with embargo, multi-seed checks, and contract-guarded deployment with normalization. It includes runnable code for data validation, features, environment, training, and broker‑based reconciliation. The live demo over 763 closed trades showed no statistically significant edge, and the methods highlight where information and costs, not architecture, set performance limits.
We are pleased to present the final part of our series on GinAR — a neural network framework for time series forecasting. In this article, we analyze the results of testing the model on new data and assess its robustness under real-market conditions.
We invite you to explore a new implementation of the key components of the GinAR framework — an adaptive algorithm for working with graph-structured time series. This article provides a step-by-step breakdown of the architecture and the algorithms for the forward pass and error backpropagation.
This article develops a visual position planning tool in MQL5 for evaluating trade setups before execution. The tool utilizes interactive Entry, Stop-Loss, and Take-Profit lines to calculate the stop distance, risk amount, estimated position size, potential reward, and risk-to-reward ratio directly on the chart. It supports market, limit, and stop order scenarios while keeping the focus strictly on planning and analysis rather than trade execution.
A state-driven Position Lifecycle Manager brings structure to post-entry trade handling in MetaTrader 5. It discovers open positions, tracks them via managed objects, applies ATR-based protection, executes break-even transitions, and removes completed trades, with a clear NEW → PROTECTED → BREAKEVEN → CLOSED flow. The article shows integration with the standard MACD EA to enable reuse across strategies.
We invite you to explore an innovative approach to forecasting time series with missing data using the GinAR framework. The article demonstrates the implementation of key components using OpenCL, which ensures high performance. In our next publication, we will take a detailed look at how to integrate these solutions into MQL5. This will help understand how to apply the method in practice in trading.
This article builds a trend-following Expert Advisor that trades momentum spillover across markets, implemented fully in MQL5 without external solvers. It detects leaders with Derivative Dynamic Time Warping, learns a sparse weighted network by convex optimization, and propagates momentum through it with a reverting response. Readers get a step-by-step, reproducible pipeline and a working EA ready to run in the Strategy Tester.
We build the Matrix Profile for MQL5 from the ground up and keep it numerically stable on real prices. The library includes rolling statistics, a radix-2 FFT powering MASS, and a STOMP self-join, with results matched to stumpy. A compact facade, an indicator that draws the profile and flags discords, and a demonstration Expert Advisor show how to read and use the signal in practice.
We invite you to learn about the K²VAE framework and how the proposed approaches can be integrated into a trading system. You will learn how the hybrid Koopman–Kalman–VAE approach helps build adaptive and interpretable models. The article concludes with practical results from using the implemented solutions.
In this article, we refine a moving average crossover strategy with a momentum candle filter and an immediate retracement bar confirmation. When both conditions are met, a pending stop order is placed using a pivot-based stop loss and a 2R take profit. The complete MQL5 Expert Advisor code, finite-state-machine logic, and chart annotations are detailed.
Bollinger Band mean reversion degrades in trending regimes when ADX is high and bandwidth expands. We separate direction from trade selection with a two‑stage meta‑labeling pipeline: a gradient‑boosted secondary classifier trained with PurgedKFold on band‑specific features (BBP, BBB, bandwidth regime) outputs action probabilities that drive probability‑based bet sizing. The MQL5 implementation loads the ONNX model and applies position sizing within a two‑EA architecture to filter low‑quality band touches.
Learn how to build an MQL5 Expert Advisor that detects and trades Larry Williams’ Oops Gap Reversal pattern using objective gap rules and later-bar confirmation. The EA tracks setup expiration, prepares stop-loss and take-profit levels, supports manual or risk-based position sizing, executes market orders, and is evaluated through historical testing.
We invite you to explore a new approach that combines classical methods and modern neural networks for time series analysis. The article provides a detailed explanation of the architecture and operating principles of the K²VAE model.
This article presents a unified news model and a set of reusable MQL5 classes for working with the MetaTrader 5 Economic Calendar. You will retrieve, filter, and cache events by time, currency, country, and importance using a single interface across three providers: built-in calendar, CSV, and SQLite. The framework supports export/import, next/previous event lookup, and reliable strategy‑tester backtesting without changing trading logic.
We evaluate blind source separation for market noise control using FastICA applied to SMA-filtered, time-lagged OHLC features. The study compares classical and surrogate targets, measures accuracy across lags, tunes KNN models, and inspects residual structure with clustering. Models are exported to ONNX and integrated into an MQL5 Expert Advisor for testing. The result is a reproducible pipeline from data extraction to deployment.
We invite you to explore the original implementation of the K²VAE framework — a flexible model capable of linearly approximating complex dynamics in latent space. This article demonstrates how to implement key components in MQL5, including parameterized matrices and how to manage them outside standard neural network layers. This material will be useful for anyone looking for a practical approach to building interpretable time-series models.
We invite you to dive into the exciting world of LightGTS — a lightweight yet powerful framework for time-series forecasting, where adaptive convolution and RoPE encoding are combined with innovative attention mechanisms. In our article, you will find a detailed description of all components — from creating patches to the complex mixture of experts in the decoder — ready for integration into MQL5 projects. Discover how LightGTS takes automated trading to a whole new level!
We invite you to embark on an exciting journey through the world of adaptive analysis of financial time series and learn how to turn complex spectral analysis and flexible convolution into real trading signals. You will see how LightGTS listens to the market rhythm, adapting to its changes through a variable-window stride, and how OpenCL acceleration can turn computation into a fast track to profitable decisions.
In this article, we will examine how to reduce risk (and whether it is even possible to do so) in option strategies where risk is initially unlimited. This applies to strategies based on writing options, i.e., range-bound strategies. We will also consider ways to lock in profits for option strategies based on purchasing options, i.e., trend-following strategies. As always, we will add new useful features to our Expert Advisor (EA) and improve the existing ones.
This article builds a Kolmogorov–Arnold Network (KAN) in MQL5, where every edge carries a learnable B‑spline curve rather than a scalar weight. We construct the spline basis, assemble edges and a layer, and fit all coefficients by ridge‑regularized least‑squares in a single solve. The model is delivered as an indicator that visualizes the learned curves and an Expert Advisor that acts on the prediction, providing an interpretable, reusable codebase.
We port Daniel Bloch's Relative Moving Average framework into a complete MetaTrader 5 system. Instead of smoothing price, the RMA measures where price sits inside its own recent distribution on a [0,1] fractile scale, and drives four cross-strategies with a regime-adaptive exit. Includes the engine, indicators, and a backtested Expert Advisor.
Although the functions we will discuss have been known for quite some time, their application in the field of trading remains terra incognita to this day. In this article, we will explore some of the opportunities these old-but-new functions offer for developing trading strategies and assess their potential.
We invite you to learn about the innovative technique of adaptive patching — a method for flexibly segmenting time series while taking their internal periodicity into account. We will also look at an efficient encoding technique that preserves important semantic characteristics when working with data at different scales. These methods open up new possibilities for the accurate processing of complex, multiscale data characteristic of financial markets and significantly improve the stability and reliability of forecasts.
We continue enhancing our modular indicator search panel by adding symbol selection capabilities. The implementation allows users to search for built-in indicators, choose a destination symbol, and attach the selected indicator without opening multiple charts or running separate Expert Advisor instances.
The article provides a fascinating look at how SwiGLU embedding reveals hidden market patterns, and how a sparse Mixture of Experts within a Decoder-Only Transformer makes forecasts more accurate at reasonable computational cost. We take an in-depth look at the integration of Time‑MoE into MQL5 and OpenCL, and provide a step-by-step guide to configuring and training the model.
The article bridges automated placement with manual analysis for the Fibonacci family in MQL5. It scans charts, identifies user Fibonacci objects, and normalizes their level arrays, interaction flags, and visuals per object type while preserving coordinates. With manual-priority enforcement, Expert Advisors can evaluate both human and code-generated tools reliably, without duplicates or runtime indexing issues.
The article provides a practical research setup for weekend gap analysis: MQL5 extracts precise pip‑based gaps and tracks fills, while Python performs statistical testing and visualization. You will compute fill rates by gap buckets, model fill probability with logistic regression, and assess time-to-fill via Kaplan–Meier curves. All steps are configurable and reproducible for EURUSD, GBPUSD, USDJPY and beyond.
We extend the supply and demand framework with a strategy layer that converts zone interactions into decisions. Qualified zones pass sequential checks for interaction proximity, approach behavior, higher‑timeframe alignment, and price action before execution is handed to a dedicated trade manager. This architecture improves control, maintainability, and future extensibility without changing the underlying zone engine.
We invite you to explore the practical implementation of a sparse mixture of experts block for time series in the OpenCL computing environment. This article provides a step-by-step explanation of how masked multi-window convolution works, as well as how gradient-based training is organized in the presence of multiple information streams.
