Articles on machine learning in trading

This work presents an end-to-end pipeline: collect MetaTrader 5 data, engineer entropy/volatility/trend features, train a PyTorch classifier, and expose predictions through a Flask API. An MQL5 EA posts rolling prices each tick, receives probability and regime, and applies adaptive position sizing and stop distances. The result is a clear recipe for integrating ML inference with MetaTrader 5.

Downloading international monetary fund data in Python: Mining IMF data for use in macroeconomic currency strategies. How can macroeconomics help an ordinary and an algorithmic trader?

In this article, we shift from Python research to native MQL5 engineering. We build the first module of the MMAR library: a shared constants header, an SVD-based OLS regression class, a Generalized Hurst Exponent estimator, and the partition analysis engine that computes the partition function, extracts tau(q), estimates H via zero-crossing interpolation, and scores multifractality through three diagnostic tests. Tested on 500,000 bars of EURUSD M10, the engine correctly classifies the data as multifractal in under four seconds. Part 4 of an eight-part series. Part 5 fits the tau(q) curve to four candidate distributions via the Legendre transform.

We port AFML Chapter 17 structural break tests to MQL5 as a single include, CStructuralBreaks, delivering six bar-indexed features for EAs: CSW statistic and critical value, Chow-Type DFC, SADF with a rolling lookback (default 252), SM-Exp, and SM-Power. SADF uses O(L²) rolling windows for real-time viability. A companion StructuralBreaksViewer indicator plots all series with per‑series visibility and optional z‑score normalization. SB_EMPTY marks invalid values for safe integration.

With the multifractal parameters from Part 2 in hand, this article builds the full MMAR process. We construct the multiplicative cascade for trading time, generate Fractional Brownian Motion via Davies-Harte FFT, and combine both into X(t) = B_H[theta(t)]. A 100-path Monte Carlo simulation produces the volatility forecast, which we then pit against GARCH on the same EURUSD M5 data. Does Mandelbrot's fractal architecture outforecast Engle's conditional variance framework? Part 3 of a eight-part series leading to a native MQL5 library and Expert Advisor.

In this article we make the case for merging Divergence Mapping with a Temporal Fusion Proxy in a Trading Robot. Rather than depending on lagging price confirmations, the Divergence Mapping's thesis is that acting like a structural sensor can help identify hidden momentum shifts from price action and indicator anomalies. To establish how these anomalies are interpreted over time we use a Temporal Fusion Transformer proxy. This network incorporates historical context to weigh developing trends such that merging it with Divergence Mapping should set us up to spot shifts in accumulation and distribution before price breakouts.

CTrailingSlidingMedianBiLSTM is a custom MQL5 Wizard trailing module that combines robust median/MAD outlier filtering with a BiLSTM context score in the range [-1, 1]. Four algorithm modes (standard, bands, RSI, adaptive) target noise, mean-reverting bursts and liquidity spikes, reducing premature stop adjustments. This module is intended for side-by-side evaluation with diverse entry signals and money management settings.

For this article we look at a custom MQL5 Wizard class for Trailing Stops. Our implemented custom class ‘CTrailingConvexHullGRU’, is built from merging the Convex Hull algorithm with a GRU network. As always we seek to develop a model that is testable with MQL5 Wizard-Assembled Expert Advisors and can be tuned with various Money Management and entry Signals classes. Our testing is with the 'Envelopes' and the RSI classes for Signal.

The article establishes a reproducible method to measure portfolio risk for multiple symbols using MQL5 matrices and OpenBLAS. It covers computing log returns, building a covariance matrix, and evaluating wᵀΣw instead of summing individual variances. A complete script prints naive versus true volatility and the cross‑term contribution, enabling you to detect when correlated instruments inflate exposure beyond single‑asset estimates.

The article diagnoses two defects that neutralize sequential bootstrap during cross‑validation: type erasure of SequentiallyBootstrappedBaggingClassifier and a fold‑level shape mismatch from cloning full samples info sets. It retains the classifier's identity, adds find seq bagging to re‑inject fold‑sliced t1 in CalibratorCV.fit, and resets state per split. A new bootstrap_comparison module reports OOF and OOB metrics and memory, letting you verify that sequential sampling is applied correctly and quantify its impact.

We continue to work on implementing the CATCH framework, which combines the Fourier transform and frequency patching mechanisms, ensuring accurate detection of market anomalies. In this article, we complete the implementation of our own vision of the proposed approaches and test the new models on real historical data.

This article presents 'CSignalUKFCapsNet', as a custom class coded in MQL5. This class is meant to be used with the MQL5 Wizard when assembling an Expert Advisor and when selected in the Wizard it defines the Expert Advisor's entry signals. In building this custom class, we brought together the algorithm Unscented Kalman Filter and the Capsule Neural Network. Our algorithm is showcased with four operation modes, and the coding of this as a custom class for the MQL5 Wizard, allows testing with various Trailing Stop methods and Money Management systems.

We test AFML's claim that the sequential bootstrap decorrelates bagged trees on overlapping triple‑barrier labels by isolating two levers: draw count and draw rule. One decision identical tree is bagged under four row‑sampling regimes and evaluated on EURUSD 2022–2023 for draw uniqueness, between‑tree correlation, AUC, and calibration. Decorrelation comes almost entirely from throttling max_samples to average uniqueness; the sequential draw adds little. Out-of-bag inflation is largest under full-count sequential sampling.

Mantis is a versatile tool for in-depth time series analysis that can be flexibly scaled to accommodate any financial scenario. Learn how a combination of patching, local convolutions, and cross-attention enables a highly accurate interpretation of market patterns.

In Part 2, we introduce a reusable CCovarianceMatrix class that computes and stores a covariance matrix from raw return series using MQL5's native Cov() method. We verify symmetry, print a labeled matrix grid, and call Eig() to obtain eigenvalues and eigenvectors. Readers see how symbols co-move and which factors drive variance, enabling clearer portfolio diagnostics and reuse in scripts or EAs.

This article implements the MMAR Simulation Engine that turns fitted parameters (H, distribution, coefficients, sample volatility) into synthetic price paths. It builds multifractal trading time via a multiplicative cascade, synthesizes fractional Brownian motion with Davies–Harte or Cholesky, scales it to target volatility, and composes the process by time deformation. Readers get a reusable MQL5 class, method choices by path length, and validation steps for scenario testing and Monte Carlo use in the next part.

This article lays out 'CMoneyKDTreeESN' custom money management class usable with the MQL5 Wizard, that combines the KD-Tree algorithm and the Echo State Network. We use the KD-Tree on log returns and ATR to give us a risk score, while the ESN tracks recent flow to give us a bounded lot size multiplier. Our class is usable in a variety of Wizard assembled Expert Advisors as shown here with the Envelopes and RSI signals, with a broad objective of modulating exposure in high-volatility and tail-risk environments.

For this article we rotate to a custom MQL5 Wizard class implementation that explores Trailing Stops. Our custom class is ‘CTrailingReservoirLinReg’ that we derive by combining the Reservoir Sampling algorithm with a Linear Regression network. As has been the case throughout these series, this formulation is testable with MQL5 Wizard Assembled Expert Advisors that can be tuned with various entry signals and money management classes.

Meet Mantis — a lightweight foundation model for time series classification based on a Transformer architecture, featuring contrastive pre-training and hybrid attention that deliver record-breaking accuracy and scalability.

The Mantis framework transforms complex time series into informative tokens and serves as a reliable foundation for an intelligent trading agent capable of operating in real time.

In this article we consider a custom MQL5 Wizard class that processes Money Management. Our custom class is labelled ‘CMoneyWaveletLSTM’, and is developed by combining the Wavelet Thresholding algorithm with an LSTM network. As has been the case throughout these series, the developed model is testable with MQL5 Wizard-Assembled Expert Advisors that can be tuned with different trailing stops and entry Signals classes. We maintain our entry Signal, as in past articles as the built-in 'Envelopes' class and the RSI class.

In today's article, we will see how a simple code change that makes a neuron slightly more specialized can significantly speed up the training stage. After all, once a neuron or neural network, as we will see later, has been trained, the work it performs becomes much faster. We will also discuss a problem that exists but is rarely mentioned.

An MQL5 port of four entropy estimators — Shannon, Plug-In, Lempel-Ziv, and Kontoyiannis — operating on the intrabar tick-rule sequence. CopyTicksRange() limits data to the broker's cached tick window, so features apply to recent bars only. The implementation encodes bid-direction ticks from MqlTick, replaces NumPy-dependent steps with array-based methods, and ships CEntropyFeatures.mqh and EntropyViewer.mq5 for EA and indicator use.

We continue our acquaintance with the Mamba4Cast framework. Today, we will delve into the practical implementation of the proposed approaches. Mamba4Cast was designed not for lengthy warm-up on every new time series, but for immediate deployment. Thanks to the concept of Zero-Shot Forecasting, the model can produce high-quality forecasts on real-world data without additional training or hyperparameter tuning.

We present a native MQL5 implementation of the catch22 feature set: all 22 canonical time-series characteristics in a reusable class validated against pycatch22. Using a leak-free pipeline (chronological split, purging, embargo), we run a three-arm ablation—classic indicators, catch22, and combined—for volatility-regime classification. Finally, we deploy the combined model as a Strategy Tester regime filter to quantify its impact on a simple baseline strategy.

Close-to-close volatility ignores the high, the low, and overnight gaps. We build a reusable MQL5 library implementing four range-based estimators from Parkinson to the gap-robust Yang-Zhang, and put it to work in a comparison indicator and a set of adaptive volatility bands.

What if lunar cycles and seasonal patterns influence the foreign exchange markets? This article shows how to translate astrological concepts into the language of mathematics and machine learning. I built a Python system with 88 features based on astronomical cycles, trained CatBoost on 15 years of EURUSD data, and obtained some intriguing results. The code is open-source, the methods are verifiable, and the conclusions are unexpected — ancient wisdom meets gradient boosting.

Mantis is a versatile tool for in-depth time series analysis that can be flexibly scaled to accommodate any financial scenario. Learn how a combination of patching, local convolutions, and cross-attention enables a highly accurate interpretation of market patterns.

Close-to-close volatility ignores the high, the low, and overnight gaps. We build a reusable MQL5 library implementing four range-based estimators from Parkinson to the gap-robust Yang-Zhang, and put it to work in a comparison indicator and a set of adaptive volatility bands.