Articles on data analysis and statistics in MQL5

We continue to study machine learning methods. With this article, we begin another big topic, Reinforcement Learning. This approach allows the models to set up certain strategies for solving the problems. We can expect that this property of reinforcement learning will open up new horizons for building trading strategies.

We have earlier discussed some types of neural network implementations. In the considered networks, the same operations are repeated for each neuron. A logical further step is to utilize multithreaded computing capabilities provided by modern technology in an effort to speed up the neural network learning process. One of the possible implementations is described in this article.

Matrices and vectors have been introduced in MQL5 for efficient operations with mathematical solutions. The new types offer built-in methods for creating concise and understandable code that is close to mathematical notation. Arrays provide extensive capabilities, but there are many cases in which matrices are much more efficient.

In this article we will check the well-known statement that "The whole day trading depends on how the Asian session is traded".

This article considers the application of multiple regression analysis to macroeconomic statistics. It also gives an insight into the evaluation of the statistics impact on the currency exchange rate fluctuation based on the example of the currency pair EURUSD. Such evaluation allows automating the fundamental analysis which becomes available to even novice traders.

The article is concerned with the problem of re-counting of the indicator value in the MetaTrader 4 Client Terminal when the null bar changes. It outlines general idea of how to add to the indicator code some extra program items that allow to restore program code saved before multiple re-counting.

In this article, I will show the criteria to be used when selecting a system or a signal for investing your funds, as well as describe the optimal approach to the development of trading systems and highlight the importance of this matter in Forex trading.

In the previous articles, we started creating a large cross-platform library simplifying the development of programs for MetaTrader 5 and MetaTrader 4 platforms. In the sixth part, we trained the library to work with positions on netting accounts. Here we will implement tracking StopLimit orders activation and prepare the functionality to track order and position modification events.

We continue to study reinforcement learning. In this article, we will get acquainted with the Deep Q-Learning method. The use of this method has enabled the DeepMind team to create a model that can outperform a human when playing Atari computer games. I think it will be useful to evaluate the possibilities of the technology for solving trading problems.

The present article develops the idea of using Kohonen Maps in MetaTrader 5, covered in some previous publications. The improved and enhanced classes provide tools to solve application tasks.

In the article, I will start developing the functionality for working with the Depth of Market. I will also create the class of the Depth of Market abstract order object and its descendants.

Understanding the subtle dynamics behind price movements can give you a critical edge. One such phenomenon is the liquidity sweep, a deliberate strategy that large traders, especially institutions, use to push prices through key support or resistance levels. These levels often coincide with clusters of retail stop-loss orders, creating pockets of liquidity that big players can exploit to enter or exit sizeable positions with minimal slippage.

In this article, I am going to improve the classes of indicator buffer objects to work in the multi-symbol mode. This will pave the way for creating multi-symbol multi-period indicators in custom programs. I will add the missing functionality to the calculated buffer objects allowing us to create multi-symbol multi-period standard indicators.

Another quarter of the year has passed and we have decided to sum up its results for MetaTrader AppStore - the largest store of trading robots and technical indicators for MetaTrader platforms. More than 500 developers have placed over 1 200 products in the Market by the end of the reported quarter.

In this article, I will complete working with chart object classes and their collection. I will also implement auto tracking of changes in chart properties and their windows, as well as saving new parameters to the object properties. Such a revision allows the future implementation of an event functionality for the entire chart collection.

We usually analyze the market using candlesticks or bars that slice the price series into regular intervals. Doesn't such discretization method distort the real structure of market movements? Discretization of an audio signal at regular intervals is an acceptable solution because an audio signal is a function that changes over time. The signal itself is an amplitude which depends on time. This signal property is fundamental.

In this article, I will start the improvement of the indicator buffer objects and collection class for working in multi-period and multi-symbol modes. I am going to consider the operation of buffer objects for receiving and displaying data from any timeframe on the current symbol chart.

This article is intended to get its readers acquainted with a possible variant of using graphical objects of the MQL5 language. It analyses an indicator, which implements a panel of managing a simple spectrum analyzer using the graphical objects. The article is meant for readers acquianted with basics of MQL5.

In this article, we’ve transitioned from manually coding candlestick‑pattern detection in Python to leveraging TA‑Lib, a library that recognizes over sixty distinct patterns. These formations offer valuable insights into potential market reversals and trend continuations. Follow along to learn more.

Estimation of statistical parameters of a sequence is very important, since most of mathematical models and methods are based on different assumptions. For example, normality of distribution law or dispersion value, or other parameters. Thus, when analyzing and forecasting of time series we need a simple and convenient tool that allows quickly and clearly estimating the main statistical parameters. The article shortly describes the simplest statistical parameters of a random sequence and several methods of its visual analysis. It offers the implementation of these methods in MQL5 and the methods of visualization of the result of calculations using the Gnuplot application.

When developing a trading system, there usually arises a problem of selecting the best combination of indicators and their signals. Discriminant analysis is one of the methods to find such combinations. The article gives an example of developing an EA for market data collection and illustrates the use of the discriminant analysis for building prognostic models for the FOREX market in Statistica software.

The article shows an example of how to develop an MQL5-program implementing the adaptive algorithm of clustering called Growing neural gas (GNG). The article is intended for the users who have studied the language documentation and have certain programming skills and basic knowledge in the area of neuroinformatics.

In the previous articles, we started creating a large cross-platform library simplifying the development of programs for MetaTrader 5 and MetaTrader 4 platforms. In the fifth part of the article series, we created trading event classes and the event collection, from which the events are sent to the base object of the Engine library and the control program chart. In this part, we will let the library to work on netting accounts.

In this article, I will expand the functionality of chart objects and arrange navigation through charts, creation of screenshots, as well as saving and applying templates to charts. Also, I will implement auto update of the collection of chart objects, their windows and indicators within them.