In the previous article, we introduced the multi-agent self-adaptive framework MASA, which combines reinforcement learning approaches and self-adaptive strategies, providing a harmonious balance between profitability and risk in turbulent market conditions. We have built the functionality of individual agents within this framework. In this article, we will continue the work we started, bringing it to its logical conclusion.
In this discussion, we contrast the classical approach to time series cross-validation with modern alternatives that challenge its core assumptions. We expose key blind spots in the traditional method—especially its failure to account for evolving market conditions. To address these gaps, we introduce Effective Memory Cross-Validation (EMCV), a domain-aware approach that questions the long-held belief that more historical data always improves performance.
We continue to develop the algorithms for FinAgent, a multimodal financial trading agent designed to analyze multimodal market dynamics data and historical trading patterns.
In this article, you will learn how to develop an Order Blocks indicator based on order book volume (market depth) and optimize it using buffers to improve accuracy. This concludes the current stage of the project and prepares for the next phase, which will include the implementation of a risk management class and a trading bot that uses signals generated by the indicator.
In this article, we'll explore one last simple use case for templates, and discuss the benefits and necessity of using typename in your code. Although this article may seem a bit complicated at first, it is important to understand it properly in order to use templates and typename later.
This article teaches you how to build an MQL5 Expert Advisor that automatically detects support and resistance zones and executes trades based on them. You’ll learn how to program your EA to identify these key market levels, monitor price reactions, and make trading decisions without manual intervention.
In this article, we propose a scoring system for mean-reversion strategies based on statistical arbitrage of cointegrated stocks. The article suggests criteria that go from liquidity and transaction costs to the number of cointegration ranks and time to mean-reversion, while taking into account the strategic criteria of data frequency (timeframe) and the lookback period for cointegration tests, which are evaluated before the score ranking properly. The files required for the reproduction of the backtest are provided, and their results are commented on as well.
Learn how to build a Smart Trade Manager Expert Advisor in MQL5 that automates trade management with break-even, trailing stop, and partial close features. A practical, step-by-step guide for traders who want to save time and improve consistency through automation.
In this article, we will create the basic functionality of a scalping Market Depth tool. Also, we will develop a tick chart based on the CGraphic library and integrate it with the order book. Using the described Market Depth, it will be possible to create a powerful assistant tool for short-term trading.
In this article, we build an MQL5 EA that detects regular RSI divergences using swing points with strength, bar limits, and tolerance checks. It executes trades on bullish or bearish signals with fixed lots, SL/TP in pips, and optional trailing stops. Visuals include colored lines on charts and labeled swings for better strategy insights.
Discover how to fix a critical flaw in financial machine learning that causes overfit models and poor live performance—label concurrency. When using the triple-barrier method, your training labels overlap in time, violating the core IID assumption of most ML algorithms. This article provides a hands-on solution through sample weighting. You will learn how to quantify temporal overlap between trading signals, calculate sample weights that reflect each observation's unique information, and implement these weights in scikit-learn to build more robust classifiers. Learning these essential techniques will make your trading models more robust, reliable and profitable.
Gamma and Delta measure how an option’s value reacts to changes in the underlying asset’s price. Delta represents the rate of change of the option’s price relative to the underlying, while Gamma measures how Delta itself changes as price moves. Together, they describe an option’s directional sensitivity and convexity—critical for dynamic hedging and volatility-based trading strategies.
The article presents the Big Bang - Big Crunch method, which has two key phases: cyclic generation of random points and their compression to the optimal solution. This approach combines exploration and refinement, allowing us to gradually find better solutions and open up new optimization opportunities.
In this discussion, we take a step forward to uncover the underlying price action hidden within candlestick wicks. By integrating a wick visualization feature into the Market Periods Synchronizer, we enhance the tool with greater analytical depth and interactivity. This upgraded system allows traders to visualize higher-timeframe price rejections directly on lower-timeframe charts, revealing detailed structures that were once concealed within the shadows.
Linear system identifcation may be coupled to learn to correct the error in a supervised learning algorithm. This allows us to build applications that depend on statistical modelling techniques without necessarily inheriting the fragility of the model's restrictive assumptions. Classical supervised learning algorithms have many needs that may be supplemented by pairing these models with a feedback controller that can correct the model to keep up with current market conditions.
We invite you to explore the FinCon framework, which is a a Large Language Model (LLM)-based multi-agent system. The framework uses conceptual verbal reinforcement to improve decision making and risk management, enabling effective performance on a variety of financial tasks.
This article introduces the “Multi-Timeframe Harmony Index”—an advanced Expert Advisor for MetaTrader 5 that calculates a weighted bias from multiple timeframes, smooths the readings using EMA, and displays the results in a clean chart panel dashboard. It includes customizable alerts and automatic buy/sell signal plotting when strong bias thresholds are crossed. Suitable for traders who use multi-timeframe analysis to align entries with overall market structure.
This article is about orthogonal polynomials. Their use can become the basis for a more accurate and effective analysis of market information allowing traders to make more informed decisions.
Sequential bootstrapping reshapes bootstrap sampling for financial machine learning by actively avoiding temporally overlapping labels, producing more independent training samples, sharper uncertainty estimates, and more robust trading models. This practical guide explains the intuition, shows the algorithm step‑by‑step, provides optimized code patterns for large datasets, and demonstrates measurable performance gains through simulations and real backtests.
In this article, we build an MQL5 EA that detects hidden RSI divergences via swing points with strength, bar ranges, tolerance, and slope angle filters for price and RSI lines. It executes buy/sell trades on validated signals with fixed lots, SL/TP in pips, and optional trailing stops for risk control.
The article presents a new metaheuristic optimization Circle Search Algorithm (CSA) based on the geometric properties of a circle. The algorithm uses the principle of moving points along tangents to find the optimal solution, combining the phases of global exploration and local exploitation.
This is a high-timeframe-based EA that makes long-term analyses, trading decisions, and executions based on higher-timeframe analyses of W1, D1, and MN. This article will explore in detail an EA that is specifically designed for long-term traders who are patient enough to withstand and hold their positions during tumultuous lower time frame price action without changing their bias frequently until take-profit targets are hit.
Simplify your MetaTrader 5 charts with the Multi Indicator Handler EA. This interactive dashboard merges trend, momentum, and volatility indicators into one real‑time panel. Switch instantly between profiles to focus on the analysis you need most. Declutter with one‑click Hide/Show controls and stay focused on price action. Read on to learn step‑by‑step how to build and customize it yourself in MQL5.
N-BEATS is a revolutionary deep learning model designed for time series forecasting. It was released to surpass classical models for time series forecasting such as ARIMA, PROPHET, VAR, etc. In this article, we are going to discuss this model and use it in predicting the stock market.
Learn how to build a clean and professional on-chart control panel in MQL5 for a Risk-Based Trade Placement Expert Advisor. This step-by-step guide explains how to design a functional GUI that allows traders to input trade parameters, calculate lot size, and prepare for automated order placement.
I invite you to explore the MacroHFT framework, which applies context-aware reinforcement learning and memory to improve high-frequency cryptocurrency trading decisions using macroeconomic data and adaptive agents.
If we are going to automate periodic optimization, we need to think about auto updates of the settings of the EAs already running on the trading account. This should also allow us to run the EA in the strategy tester and change its settings within a single run.
In the second installment of the series, we discuss the properties of bivariate Archimedean copulae and their implementation in MQL5. We also explore applying copulae to the development of a simple pairs trading strategy.
This part explores how to design a Dynamic Multi-Pair Expert Advisor capable of adapting between Scalping and Swing Trading modes. It covers the structural and algorithmic differences in signal generation, trade execution, and risk management, allowing the EA to intelligently switch strategies based on market behavior and user input.
This article helps new community members search for and discover their own candlestick patterns. Describing these patterns can be daunting, as it requires manually searching and creatively identifying improvements. Here, we introduce the engulfing candlestick pattern and show how it can be enhanced for more profitable trading applications.
Factorization is a mathematical process used to gain insights into the attributes of data. When we apply factorization to large sets of market data — organized in rows and columns — we can uncover patterns and characteristics of the market. Factorization is a powerful tool, and this article will show how you can use it within the MetaTrader 5 terminal, through the MQL5 API, to gain more profound insights into your market data.
In this article, we develop an MQL5 Expert Advisor for statistical mean reversion trading, calculating moments like mean, variance, skewness, kurtosis, and Jarque-Bera statistics over a specified period to identify non-normal distributions and generate buy/sell signals based on confidence intervals with adaptive thresholds
Historical data is far from “trash”—it’s the foundation of any robust market analysis. In this article, we’ll take you step‑by‑step from collecting that history to using it to train a predictive model, and finally deploying that model for live price forecasts. Read on to learn how!
In this article, we develop an MQL5 strategy tracker system that detects moving average crossover signals filtered by a long-term MA, simulates or executes trades with configurable TP levels and SL in points, and monitors outcomes like TP/SL hits for performance analysis.
Learn how to build an interactive MQL5 Expert Advisor with an on-chart control panel. Know how to compute risk-based lot sizes and place trades directly from the chart.
We will use a quantum computer from IBM to discover all price movement options. Sounds like science fiction? Welcome to the world of quantum computing for trading!
In Part 5 of our MQL5 AI trading system series, we enhance the ChatGPT-integrated Expert Advisor by introducing a collapsible sidebar, improving navigation with small and large history popups for seamless chat selection, while maintaining multiline input handling, persistent encrypted chat storage, and AI-driven trade signal generation from chart data.
In this part, we focus on how to merge real-time market feedback—such as live trade outcomes, volatility changes, and liquidity shifts—with adaptive model learning to maintain a responsive and self-improving trading system.
We created a log suppression system in the Logify library. It details how the CLogifySuppression class reduces console noise by applying configurable rules to avoid repetitive or irrelevant messages. We also cover the external configuration framework, validation mechanisms, and comprehensive testing to ensure robustness and flexibility in log capture during bot or indicator development.
All algorithmic trading strategies are difficult to set up and maintain, regardless of complexity—a challenge shared by beginners and experts alike. This article introduces an ensemble framework where supervised models and human intuition work together to overcome their shared limitations. By aligning a moving average channel strategy with a Ridge Regression model on the same indicators, we achieve centralized control, faster self-correction, and profitability from otherwise unprofitable systems.
