Articles on data analysis and statistics in MQL5

In the previous article, we completed the necessary introduction to SQL. And, in my opinion, we properly clarified what we wanted to show and explain about SQL. This was done so that anyone who comes to look at the market replay/simulation system being built can at least get an idea of what may be happening there. The point is that there is no sense in programming things that SQL handles perfectly.

The article explains how to develop a tool for analyzing recurring price patterns in financial markets — by day of the month (1-31), day of the week (Monday-Sunday), or hour of the day (0-23). The indicator analyzes historical data, calculates the average return for each period, and displays the results as a histogram with a forecast. It includes customizable parameters: seasonality type, number of bars analyzed, display as percentages or absolute values, chart colors.

For this article we switch to a custom MQL5 Wizard class implementation that explores Money Management. We are labelling our custom class ‘CMoneySuffixAE’ that we derive by combining the Suffix Automaton algorithm with an Autoencoder neural network. As always, this formulation is testable with MQL5 Wizard Assembled Expert Advisors that can be tuned with various entry signals and trailing stop approaches.

The article presents a detailed analysis of the Exchange Market Algorithm (EMA) inspired by the behavior of stock market traders. The algorithm simulates stock trading, where market participants with varying levels of success employ different strategies to maximize profits.

We extend the RQA library for MetaTrader 5 with JRQA, which detects when two series simultaneously revisit their own past states. The article covers the joint recurrence matrix, twelve JRQA metrics (including TREND and COMPLEXITY), dual-epsilon configuration, and a rolling-window engine with OpenCL acceleration and automatic CPU fallback. A practical indicator plots JRR, JDET, JLAM, JENTR, and JTREND for any symbol pair with timestamp alignment and normalization.

This article extends the MQL5 RQA library to Cross-Recurrence Quantification Analysis (CRQA) for comparing two time series. We implement dual‑series embedding, cross‑recurrence matrix construction, adapted metrics (CRR, CDET, CLAM, CENTR, and others), and rolling‑window analysis, with optional GPU acceleration via OpenCL. A ready-to-use indicator compares two symbols in real time, supporting timestamp alignment and normalization for practical inter-market analysis.

Part 2 focuses on practical long-memory detection for intraday data. Three complementary Hurst estimators are implemented and combined into a confidence‑weighted composite, with confidence tied to valid regression scales. The final H and confidence populate the shared analysis struct, enabling indicators to act only when H departs from the neutral 0.40–0.60 band and to select trend‑following above 0.60 or mean‑reversion below 0.40.

The article explores the possibility of using regression models in algorithmic trading. Regression models, unlike binary classification, allow for the creation of more flexible trading strategies by quantifying predicted price changes.

For our next Exploration on notions that are testable with the MQL5 Wizard we examine if Skip Lists and the Hopfield Network can give us a profit-guarding trailing strategy. Trailing Stop Management, as already argued, can be overlooked in most trading systems at the expense of Entry Signals or even Money Management. Trailing stops can make all the difference in certain situations such as trending markets, and thus we test this out with GBP USD.

The article extends the MQL5 recurrence library to Recurrence Network Analysis (RNA) by treating recurrence matrices as adjacency matrices of undirected graphs. It implements core network metrics—clustering, transitivity, average path length, betweenness, assortativity, and density—and applies them in rolling windows for single-series RNA and Joint RNA (JRNA). A modular metrics engine and two indicators visualize the evolving network structure on MetaTrader 5 charts for practical time-series analysis.

This article builds the Spectrum Fitter: from tau(q) we compute f(alpha) with a discrete Legendre transform, then fit Normal, Binomial, Poisson, and Gamma spectra under box constraints using BLEIC. The best model by SSE is selected, and its parameters (eg, alpha min, alpha max or alpha_0, gamma) become the cascade inputs for multifractal simulation.

In today's article we will begin studying the use of SQL in MQL5 code. We will also look at how to create a database. Or, more precisely, how to create a SQLite database file using the features built into MQL5. We will also see how to create a table, and then how to establish a relationship between tables by using primary and foreign keys. All of this, once again, will be done with MQL5. We will see how easy it is to create code that can later be migrated to other SQL implementations by using a class that helps hide the implementation being created. And, most importantly, we will see that at various points we may face the risk that something will go wrong when using SQL. This happens because, in MQL5 code, SQL code will always be placed inside a string.

The article discusses the Extremal Optimization (EO) algorithm, an optimization method inspired by the Bak-Sneppen self-organized criticality model, where evolution occurs through the elimination of the worst-case components of the system. The modified population version of the algorithm demonstrates a shift away from theoretical principles in favor of practical efficiency, leading to the creation of powerful computational tools.