Neural networks made easy (Part 60): Online Decision Transformer (ODT)
The last two articles were devoted to the Decision Transformer method, which models action sequences in the context of an autoregressive model of desired rewards. In this article, we will look at another optimization algorithm for this method.
Automating Trading Strategies in MQL5 (Part 32): Creating a Price Action 5 Drives Harmonic Pattern System
In this article, we develop a 5 Drives pattern system in MQL5 that identifies bullish and bearish 5 Drives harmonic patterns using pivot points and Fibonacci ratios, executing trades with customizable entry, stop loss, and take-profit levels based on user-selected options. We enhance trader insight with visual feedback through chart objects like triangles, trendlines, and labels to clearly display the A-B-C-D-E-F pattern structure.
Estimate future performance with confidence intervals
In this article we delve into the application of boostrapping techniques as a means to estimate the future performance of an automated strategy.
Category Theory in MQL5 (Part 7): Multi, Relative and Indexed Domains
Category Theory is a diverse and expanding branch of Mathematics which is only recently getting some coverage in the MQL5 community. These series of articles look to explore and examine some of its concepts & axioms with the overall goal of establishing an open library that provides insight while also hopefully furthering the use of this remarkable field in Traders' strategy development.
Neural networks made easy (Part 39): Go-Explore, a different approach to exploration
We continue studying the environment in reinforcement learning models. And in this article we will look at another algorithm – Go-Explore, which allows you to effectively explore the environment at the model training stage.
Neural Networks in Trading: State Space Models
A large number of the models we have reviewed so far are based on the Transformer architecture. However, they may be inefficient when dealing with long sequences. And in this article, we will get acquainted with an alternative direction of time series forecasting based on state space models.
Introduction to MQL5 (Part 21): Automating Harmonic Pattern Detection
Learn how to detect and display the Gartley harmonic pattern in MetaTrader 5 using MQL5. This article explains each step of the process, from identifying swing points to applying Fibonacci ratios and plotting the full pattern on the chart for clear visual confirmation.
Neural Networks in Trading: Dual-Attention-Based Trend Prediction Model
We continue the discussion about the use of piecewise linear representation of time series, which was started in the previous article. Today we will see how to combine this method with other approaches to time series analysis to improve the price trend prediction quality.
Creating a Trading Administrator Panel in MQL5 (Part V): Two-Factor Authentication (2FA)
Today, we will discuss enhancing security for the Trading Administrator Panel currently under development. We will explore how to implement MQL5 in a new security strategy, integrating the Telegram API for two-factor authentication (2FA). This discussion will provide valuable insights into the application of MQL5 in reinforcing security measures. Additionally, we will examine the MathRand function, focusing on its functionality and how it can be effectively utilized within our security framework. Continue reading to discover more!
From Novice to Expert: Collaborative Debugging in MQL5
Problem-solving can establish a concise routine for mastering complex skills, such as programming in MQL5. This approach allows you to concentrate on solving problems while simultaneously developing your skills. The more problems you tackle, the more advanced expertise is transferred to your brain. Personally, I believe that debugging is the most effective way to master programming. Today, we will walk through the code-cleaning process and discuss the best techniques for transforming a messy program into a clean, functional one. Read through this article and uncover valuable insights.
Price Action Analysis Toolkit Development (Part 14): Parabolic Stop and Reverse Tool
Embracing technical indicators in price action analysis is a powerful approach. These indicators often highlight key levels of reversals and retracements, offering valuable insights into market dynamics. In this article, we demonstrate how we developed an automated tool that generates signals using the Parabolic SAR indicator.
Neural Networks in Trading: Unified Trajectory Generation Model (UniTraj)
Understanding agent behavior is important in many different areas, but most methods focus on just one of the tasks (understanding, noise removal, or prediction), which reduces their effectiveness in real-world scenarios. In this article, we will get acquainted with a model that can adapt to solving various problems.
Automating Trading Strategies in MQL5 (Part 38): Hidden RSI Divergence Trading with Slope Angle Filters
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.
Neural Networks Made Easy (Part 84): Reversible Normalization (RevIN)
We already know that pre-processing of the input data plays a major role in the stability of model training. To process "raw" input data online, we often use a batch normalization layer. But sometimes we need a reverse procedure. In this article, we discuss one of the possible approaches to solving this problem.
Building a Candlestick Trend Constraint Model (Part 10): Strategic Golden and Death Cross (EA)
Did you know that the Golden Cross and Death Cross strategies, based on moving average crossovers, are some of the most reliable indicators for identifying long-term market trends? A Golden Cross signals a bullish trend when a shorter moving average crosses above a longer one, while a Death Cross indicates a bearish trend when the shorter average moves below. Despite their simplicity and effectiveness, manually applying these strategies often leads to missed opportunities or delayed trades.
Neural networks made easy (Part 46): Goal-conditioned reinforcement learning (GCRL)
In this article, we will have a look at yet another reinforcement learning approach. It is called goal-conditioned reinforcement learning (GCRL). In this approach, an agent is trained to achieve different goals in specific scenarios.
Neural networks made easy (Part 78): Decoder-free Object Detector with Transformer (DFFT)
In this article, I propose to look at the issue of building a trading strategy from a different angle. We will not predict future price movements, but will try to build a trading system based on the analysis of historical data.
Developing a multi-currency Expert Advisor (Part 3): Architecture revision
We have already made some progress in developing a multi-currency EA with several strategies working in parallel. Considering the accumulated experience, let's review the architecture of our solution and try to improve it before we go too far ahead.
News Trading Made Easy (Part 5): Performing Trades (II)
This article will expand on the trade management class to include buy-stop and sell-stop orders to trade news events and implement an expiration constraint on these orders to prevent any overnight trading. A slippage function will be embedded into the expert to try and prevent or minimize possible slippage that may occur when using stop orders in trading, especially during news events.
Neural networks made easy (Part 45): Training state exploration skills
Training useful skills without an explicit reward function is one of the main challenges in hierarchical reinforcement learning. Previously, we already got acquainted with two algorithms for solving this problem. But the question of the completeness of environmental research remains open. This article demonstrates a different approach to skill training, the use of which directly depends on the current state of the system.
Neural networks made easy (Part 51): Behavior-Guided Actor-Critic (BAC)
The last two articles considered the Soft Actor-Critic algorithm, which incorporates entropy regularization into the reward function. This approach balances environmental exploration and model exploitation, but it is only applicable to stochastic models. The current article proposes an alternative approach that is applicable to both stochastic and deterministic models.
Creating a Trading Administrator Panel in MQL5 (Part IX): Code Organization (IV): Trade Management Panel class
This discussion covers the updated TradeManagementPanel in our New_Admin_Panel EA. The update enhances the panel by using built-in classes to offer a user-friendly trade management interface. It includes trading buttons for opening positions and controls for managing existing trades and pending orders. A key feature is the integrated risk management that allows setting stop loss and take profit values directly in the interface. This update improves code organization for large programs and simplifies access to order management tools, which are often complex in the terminal.
MQL5 Trading Tools (Part 7): Informational Dashboard for Multi-Symbol Position and Account Monitoring
In this article, we develop an informational dashboard in MQL5 for monitoring multi-symbol positions and account metrics like balance, equity, and free margin. We implement a sortable grid with real-time updates, CSV export, and a glowing header effect to enhance usability and visual appeal.
MQL5 Wizard Techniques you should know (Part 16): Principal Component Analysis with Eigen Vectors
Principal Component Analysis, a dimensionality reducing technique in data analysis, is looked at in this article, with how it could be implemented with Eigen values and vectors. As always, we aim to develop a prototype expert-signal-class usable in the MQL5 wizard.
Reimagining Classic Strategies (Part V): Multiple Symbol Analysis on USDZAR
In this series of articles, we revisit classical strategies to see if we can improve the strategy using AI. In today's article, we will examine a popular strategy of multiple symbol analysis using a basket of correlated securities, we will focus on the exotic USDZAR currency pair.
Automating Trading Strategies in MQL5 (Part 39): Statistical Mean Reversion with Confidence Intervals and Dashboard
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
Chaos theory in trading (Part 1): Introduction, application in financial markets and Lyapunov exponent
Can chaos theory be applied to financial markets? In this article, we will consider how conventional Chaos theory and chaotic systems are different from the concept proposed by Bill Williams.
Trading with the MQL5 Economic Calendar (Part 5): Enhancing the Dashboard with Responsive Controls and Filter Buttons
In this article, we create buttons for currency pair filters, importance levels, time filters, and a cancel option to improve dashboard control. These buttons are programmed to respond dynamically to user actions, allowing seamless interaction. We also automate their behavior to reflect real-time changes on the dashboard. This enhances the overall functionality, mobility, and responsiveness of the panel.
Combine Fundamental And Technical Analysis Strategies in MQL5 For Beginners
In this article, we will discuss how to integrate trend following and fundamental principles seamlessly into one Expert Advisors to build a strategy that is more robust. This article will demonstrate how easy it is for anyone to get up and running building customized trading algorithms using MQL5.
Reimagining Classic Strategies (Part VI): Multiple Time-Frame Analysis
In this series of articles, we revisit classic strategies to see if we can improve them using AI. In today's article, we will examine the popular strategy of multiple time-frame analysis to judge if the strategy would be enhanced with AI.
Self Optimizing Expert Advisors in MQL5 (Part 10): Matrix Factorization
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.
From Novice to Expert: Animated News Headline Using MQL5 (IX) — Multiple Symbol Management on a single chart for News Trading
News trading often requires managing multiple positions and symbols within a very short time due to heightened volatility. In today’s discussion, we address the challenges of multi-symbol trading by integrating this feature into our News Headline EA. Join us as we explore how algorithmic trading with MQL5 makes multi-symbol trading more efficient and powerful.
Neural Networks in Trading: Lightweight Models for Time Series Forecasting
Lightweight time series forecasting models achieve high performance using a minimum number of parameters. This, in turn, reduces the consumption of computing resources and speeds up decision-making. Despite being lightweight, such models achieve forecast quality comparable to more complex ones.
Automating Black-Scholes Greeks: Advanced Scalping and Microstructure Trading
Gamma and Delta were originally developed as risk-management tools for hedging options exposure, but over time they evolved into powerful instruments for advanced scalping, order-flow modeling, and microstructure trading. Today, they serve as real-time indicators of price sensitivity and liquidity behavior, enabling traders to anticipate short-term volatility with remarkable precision.
Neural Networks in Trading: Contrastive Pattern Transformer
The Contrastive Transformer is designed to analyze markets both at the level of individual candlesticks and based on entire patterns. This helps improve the quality of market trend modeling. Moreover, the use of contrastive learning to align representations of candlesticks and patterns fosters self-regulation and improves the accuracy of forecasts.
From Novice to Expert: Parameter Control Utility
Imagine transforming the traditional EA or indicator input properties into a real-time, on-chart control interface. This discussion builds upon our foundational work in the Market Period Synchronizer indicator, marking a significant evolution in how we visualize and manage higher-timeframe (HTF) market structures. Here, we turn that concept into a fully interactive utility—a dashboard that brings dynamic control and enhanced multi-period price action visualization directly onto the chart. Join us as we explore how this innovation reshapes the way traders interact with their tools.
Trading with the MQL5 Economic Calendar (Part 4): Implementing Real-Time News Updates in the Dashboard
This article enhances our Economic Calendar dashboard by implementing real-time news updates to keep market information current and actionable. We integrate live data fetching techniques in MQL5 to update events on the dashboard continuously, improving the responsiveness of the interface. This update ensures that we can access the latest economic news directly from the dashboard, optimizing trading decisions based on the freshest data.
Formulating Dynamic Multi-Pair EA (Part 2): Portfolio Diversification and Optimization
Portfolio Diversification and Optimization strategically spreads investments across multiple assets to minimize risk while selecting the ideal asset mix to maximize returns based on risk-adjusted performance metrics.
Neural Networks in Trading: Controlled Segmentation (Final Part)
We continue the work started in the previous article on building the RefMask3D framework using MQL5. This framework is designed to comprehensively study multimodal interaction and feature analysis in a point cloud, followed by target object identification based on a description provided in natural language.
Neural Networks Made Easy (Part 85): Multivariate Time Series Forecasting
In this article, I would like to introduce you to a new complex timeseries forecasting method, which harmoniously combines the advantages of linear models and transformers.