Articles on the MQL5 programming and use of trading robots

Data classification for purposes of analysis and forecasting is a very diverse arena within machine learning and it features a large number of approaches and methods. This piece looks at one such approach, namely Agglomerative Hierarchical Classification.

We commence a new article series that builds upon our earlier efforts laid out in the MQL5 Wizard series, by taking them further as we step up our approach to systematic trading and strategy testing. Within these new series, we’ll concentrate our focus on Expert Advisors that are coded to hold only a single type of position - primarily longs. Focusing on just one market trend can simplify analysis, lessen strategy complexity and expose some key insights, especially when dealing in assets beyond forex. Our series, therefore, will investigate if this is effective in equities and other non-forex assets, where long only systems usually correlate well with smart money or institution strategies.

In the last article, we examined the pairing of Ichimoku and the ADX under an Inference Learning framework. For this piece we revisit, Reinforcement Learning when used with an indicator pairing we considered last in ‘Part 68’. The TRIX and Williams Percent Range. Our algorithm for this review will be the Quantile Regression DQN. As usual, we present this as a custom signal class designed for implementation with the MQL5 Wizard.

We continue our examination of the StockFormer hybrid trading system, which combines predictive coding and reinforcement learning algorithms for financial time series analysis. The system is based on three Transformer branches with a Diversified Multi-Head Attention (DMH-Attn) mechanism that enables the capturing of complex patterns and interdependencies between assets. Previously, we got acquainted with the theoretical aspects of the framework and implemented the DMH-Attn mechanisms. Today, we will talk about the model architecture and training.

We invite you to explore a framework that combines wavelet transforms and a multi-task self-attention model, aimed at improving the responsiveness and accuracy of forecasting in volatile market conditions. The wavelet transform allows asset returns to be decomposed into high and low frequencies, carefully capturing long-term market trends and short-term fluctuations.

We follow up on our last article, where we introduced the indicator couple of the Awesome-Oscillator and the Envelope Channel, by looking at how this pairing could be enhanced with Supervised Learning. The Awesome-Oscillator and Envelope-Channel are a trend-spotting and support/resistance complimentary mix. Our supervised learning approach is a CNN that engages the Dot Product Kernel with Cross-Time-Attention to size its kernels and channels. As per usual, this is done in a custom signal class file that works with the MQL5 wizard to assemble an Expert Advisor.

In this article, we will discuss the Mask-Attention-Free Transformer (MAFT) method and its application in the field of trading. Unlike traditional Transformers that require data masking when processing sequences, MAFT optimizes the attention process by eliminating the need for masking, significantly improving computational efficiency.

The CATCH framework combines Fourier transform and frequency patching to accurately identify market anomalies beyond the reach of traditional methods. Let us examine how this approach reveals hidden patterns in financial data.

Monte-Carlo is the fourth different algorithm in reinforcement learning that we are considering with the aim of exploring its implementation in wizard assembled Expert Advisors. Though anchored in random sampling, it does present vast ways of simulation which we can look to exploit.

In this article, we enhance the 3D binomial distribution graphing tool in MQL5 by adding a segmented 3D curve for improved depth perception of the probability mass function, integrating pan mode for view target shifting, and implementing an interactive view cube with hover zones and animations for quick orientation changes. We incorporate clickable sub-zones on the view cube for faces, edges, and corners to animate camera transitions to standard views, while maintaining switchable 2D/3D modes, real-time updates, and customizable parameters for immersive probabilistic analysis in trading.

The Accelerator Oscillator is another Bill Williams Indicator that tracks price momentum's acceleration and not just its pace. Although much like the Awesome oscillator we reviewed in a recent article, it seeks to avoid the lagging effects by focusing more on acceleration as opposed to just speed. We examine as always what patterns we can get from this and also what significance each could have in trading via a wizard assembled Expert Advisor.

In this article, we enhance the canvas-based price dashboard in MQL5 by adding a pixel-perfect scrollable text panel for usage guides, overcoming native scrolling limitations through custom antialiasing and a rounded scrollbar design with hover-expand functionality. The text panel supports themed backgrounds with opacity, dynamic line wrapping for content like instructions and contacts, and interactive navigation via up/down buttons, slider dragging, and mouse wheel scrolling within the body area.

This article implements a static, CSV-based news source for the Strategy Tester, so historical economic news events can be preloaded and queried during backtesting. It replaces live calendar calls in tester mode with a fast in-memory search, preserves the live logic for trading, and delivers deterministic, repeatable results with explicit control over included events, enabling reliable validation of news-aware filters, stop suspension, and trade-blocking rules.

Financial markets are not perfectly balanced. Some markets are bullish, some are bearish, and some exhibit some ranging behaviors indicating uncertainty in either direction, this unbalanced information when used to train machine learning models can be misleading as the markets change frequently. In this article, we are going to discuss several ways to tackle this issue.

The DeMarker Oscillator and the Envelope indicator are momentum and support/resistance tools that can be paired when developing an Expert Advisor. We therefore examine on a pattern by pattern basis what could be of use and what potentially avoid. We are using, as always, a wizard assembled Expert Advisor together with the Patterns-Usage functions that are built into the Expert Signal Class.

The RSI is a popular momentum oscillator that measures pace and size of a security’s recent price change to evaluate over-and-under valued situations in the security’s price. These insights in speed and magnitude are key in defining reversal points. We put this oscillator to work in another custom signal class and examine the traits of some of its signals. We start, though, by wrapping up what we started previously on Bollinger Bands.

Replay buffers in Reinforcement Learning are particularly important with off-policy algorithms like DQN or SAC. This then puts the spotlight on the sampling process of this memory-buffer. While default options with SAC, for instance, use random selection from this buffer, Prioritized Experience Replay buffers fine tune this by sampling from the buffer based on a TD-score. We review the importance of Reinforcement Learning, and, as always, examine just this hypothesis (not the cross-validation) in a wizard assembled Expert Advisor.

This piece follows up ‘Part-84’, where we introduced the pairing of Stochastic and the Fractal Adaptive Moving Average. We now shift focus to Inference Learning, where we look to see if laggard patterns in the last article could have their fortunes turned around. The Stochastic and FrAMA are a momentum-trend complimentary pairing. For our inference learning, we are revisiting the Beta algorithm of a Variational Auto Encoder. We also, as always, do the implementation of a custom signal class designed for integration with the MQL5 Wizard.

The article describes and codes MR Swing in MQL5, a mean‑reversion swing approach that combines a 200‑day hysteresis channel with Value Charts, DVO, and SVAPO. We document entry/exit rules for bull and bear regimes and show five‑year backtests on six high‑liquidity Nasdaq stocks. The complete EA code and backtest configurations are provided for reproducibility.

During the offline learning, we optimize the Agent's policy based on the training sample data. The resulting strategy gives the Agent confidence in its actions. However, such optimism is not always justified and can cause increased risks during the model operation. Today we will look at one of the methods to reduce these risks.

Restricted Boltzmann Machines are a form of neural network that was developed in the mid 1980s at a time when compute resources were prohibitively expensive. At its onset, it relied on Gibbs Sampling and Contrastive Divergence in order to reduce dimensionality or capture the hidden probabilities/properties over input training data sets. We examine how Backpropagation can perform similarly when the RBM ‘embeds’ prices for a forecasting Multi-Layer-Perceptron.

We consider XLY, SPDR’s consumer discretionary spending ETF and see if with tools in MetaTrader’s IDE we can sift through an array of data sets in selecting what could work with a forecasting model with a forward outlook of not more than a year.

There is a powerful and pervasive force quietly corrupting the collective efforts of our community to build reliable trading strategies that employ AI in any shape or form. This article establishes that part of the problems we face, are rooted in blind adherence to "best practices". By furnishing the reader with simple real-world market-based evidence, we will reason to the reader why we must refrain from such conduct, and rather adopt domain-bound best practices if our community should stand any chance of recovering the latent potential of AI.

The MacroHFT framework for high-frequency cryptocurrency trading uses context-aware reinforcement learning and memory to adapt to dynamic market conditions. At the end of this article, we will test the implemented approaches on real historical data to assess their effectiveness.

This article is somewhat different from my earlier publications. In this article, we will talk about an alternative representation of time series. Piecewise linear representation of time series is a method of approximating a time series using linear functions over small intervals.

Most modern multimodal time series forecasting methods use the independent channels approach. This ignores the natural dependence of different channels of the same time series. Smart use of two approaches (independent and mixed channels) is the key to improving the performance of the models.

Effective identification and preservation of the local structure of market data in noisy conditions is a critical task in trading. The use of the Self-Attention mechanism has shown promising results in processing such data; however, the classical approach does not account for the local characteristics of the underlying structure. In this article, I introduce an algorithm capable of incorporating these structural dependencies.

In this article, we take our second attempt to convert the changes in price levels on any market, into a corresponding change in angle. This time around, we selected a more mathematically sophisticated approach than we selected in our first attempt, and the results we obtained suggest that our change in approach may have been the right decision. Join us today, as we discuss how we can use Polar coordinates to calculate the angle formed by changes in price levels, in a meaningful way, regardless of which market you are analyzing.

Regularization is a form of penalizing the loss function in proportion to the discrete weighting applied throughout the various layers of a neural network. We look at the significance, for some of the various regularization forms, this can have in test runs with a wizard assembled Expert Advisor.

This article presents a Time-of-Day capital rotation engine for MQL5 that allocates risk by trading session instead of using uniform exposure. We detail session budgets within a daily risk cap, dynamic lot sizing from remaining session risk, and automatic daily resets. Execution uses session-specific breakout and fade logic with ATR-based volatility confirmation. Readers gain a practical template to deploy capital where session conditions are statistically strongest while keeping exposure controlled throughout the day.

Direct point cloud analysis avoids unnecessary data growth and improves the performance of models in classification and segmentation tasks. Such approaches demonstrate high performance and robustness to perturbations in the original data.

In this article, we will talk about algorithms for using attention methods in solving problems of detecting objects in a point cloud. Object detection in point clouds is important for many real-world applications.

We follow up our last article, where we introduced the indicator pair of the SAR and the RVI, by considering how this indicator pairing could be extended with Machine Learning. SAR and RVI are a trend and momentum complimentary pairing. Our machine learning approach uses a convolution neural network that engages the Exponential kernel in sizing its kernels and channels, when fine-tuning the forecasts of this indicator pairing. As always, this is done in a custom signal class file that works with the MQL5 wizard to assemble an Expert Advisor.

The article introduces a restart-safe storage model for news-time stop removal. Suspension state and original SL/TP per position are written to terminal global variables, reconstructed on OnInit, and cleaned after restoration. This lets the EA resume an active suspension window after recompiles or restarts and restore stops only when the news window ends.