As a continuation of the neural network topic, I propose considering convolutional neural networks. This type of neural network are usually applied to analyzing visual imagery. In this article, we will consider the application of these networks in the financial markets.
This article describes one of the possible approaches to data transformation aimed at improving the generalizability of the model, and also discusses sampling and selection of CatBoost models.
The article considers the methodology for developing trading algorithms, in which a consistent scientific approach is used to analyze possible price patterns and to build trading algorithms based on these patterns. Development ideals are demonstrated using examples.
The article provides the code and the description of the main stages of the machine learning process using a specific example. To obtain the model, you do not need Python or R knowledge. Furthermore, basic MQL5 knowledge is enough — this is exactly my level. Therefore, I hope that the article will serve as a good tutorial for a broad audience, assisting those interested in evaluating machine learning capabilities and in implementing them in their programs.
The article is devoted to the programmatic generation of custom symbols which are used to demonstrate some popular methods for displaying quotes. It describes a suggested variant of minimally invasive adaptation of Expert Advisors for trading a real symbol from a derived custom symbol chart. MQL source codes are attached to this article.
In this article, we will expand the capabilities of the toolkit: we will add the ability to close trade positions upon specific conditions and will create tables for controlling market and pending orders, with the ability to edit these orders.
In this article, we consider the principles of mathematical expression parsing and evaluation using parsers based on operator precedence. We will implement Pratt and shunting-yard parser, byte-code generation and calculations by this code, as well as view how to use indicators as functions in expressions and how to set up trading signals in Expert Advisors based on these indicators.
Today, many traders switch to automated trading systems which can require additional setup or can be fully automated and ready to use. However, there is a considerable part of traders who prefer trading manually, in the old fashioned way. In this article, we will create toolkit for quick manual trading, using hotkeys, and for performing typical trading actions in one click.
Markets dropped down by more that 30% within one month. It seems to be the best time for testing grid- and martingale-based Expert Advisors. This article is an unplanned continuation of the series "Creating a Cross-Platform Grid EA". The current market provides an opportunity to arrange a stress rest for the grid EA. So, let's use this opportunity and test our Expert Advisor.
The article offers basic tools for the OLAP analysis of tester reports relating to single passes and optimization results. The tool can work with standard format files (tst and opt), and it also provides a graphical interface. MQL source codes are attached below.
This article deals with the theory and practical application of the algorithm for forecasting time series, based on support-vector method. It also proposes its implementation in MQL and provides test indicators and Expert Advisors. This technology has not been implemented in MQL yet. But first, we have to get to know math for it.
This article deals with the theory and practical use of the algorithm for forecasting time series, based on the empirical decomposition mode. It proposes the MQL implementation of this method and presents test indicators and Expert Advisors.
In this article we will continue dealing with the OLAP technology applied to trading. We will expand the functionality presented in the first two articles. This time we will consider the operational analysis of quotes. We will put forward and test the hypotheses on trading strategies based on aggregated historical data. The article presents Expert Advisors for studying bar patterns and adaptive trading.
The article presents an extended study of seasonal characteristics: autocorrelation heat maps and scatter plots. The purpose of the article is to show that "market memory" is of seasonal nature, which is expressed through maximized correlation of increments of arbitrary order.
When developing indicators, Expert Advisors and scripts, developers often need to create various pieces of code, which are not directly related to the trading strategy. In this article, we consider a way to create Expert Advisors using earlier created blocks, such as trailing, filtering and scheduling code, among others. We will see the benefits of this programming approach.
In this article, we will consider the class of displaying text messages. Currently, we have a sufficient number of different text messages. It is time to re-arrange the methods of their storage, display and translation of Russian or English messages to other languages. Besides, it would be good to introduce convenient ways of adding new languages to the library and quickly switching between them.
The article arranges the work of an account object on a new base object of all library objects, improves the CBaseObj base object and tests setting tracked parameters, as well as receiving events for any library objects.
In previous articles within this series, we tried various methods for creating a more or less profitable grid Expert Advisor. Now we will try to increase the EA profitability through diversification. Our ultimate goal is to reach 100% profit per year with the maximum balance drawdown no more than 20%.
The article provides a critical examination of regular divergence and efficiency of various indicators. In addition, it contains filtering options for an increased analysis accuracy and features description of non-standard solutions. As a result, we will create a new tool for solving the technical task.
In this article, we will make an attempt to develop the best possible grid-based EA. As usual, this will be a cross-platform EA capable of working both with MetaTrader 4 and MetaTrader 5. The first EA was good enough, except that it could not make a profit over a long period of time. The second EA could work at intervals of more than several years. Unfortunately, it was unable to yield more than 50% of profit per year with a maximum drawdown of less than 50%.
In this article, we will develop a grider EA for trading in a trend direction within a range. Thus, the EA is to be suited mostly for Forex and commodity markets. According to the tests, our grider showed profit since 2018. Unfortunately, this is not true for the period of 2014-2018.
In this article, we consider the creation of an interactive graphical interface for an MQL program, which is designed for the processing of account history and trading reports using OLAP techniques. To obtain a visual result, we will use maximizable and scalable windows, an adaptive layout of rubber controls and a new control for displaying diagrams. To provide the visualization functionality, we will implement a GUI with the selection of variables along coordinate axes, as well as with the selection of aggregate functions, diagram types and sorting options.
The article describes how to create a framework for the online analysis of multidimensional data (OLAP), as well as how to implement this in MQL and to apply such analysis in the MetaTrader environment using the example of trading account history processing.
In this article, we will learn how to create Expert Advisors (EAs) working both in MetaTrader 4 and MetaTrader 5. To do this, we are going to develop an EA constructing order grids. Griders are EAs that place several limit orders above the current price and the same number of limit orders below it simultaneously.
The article provides a description of a universal method for analyzing and converting data from HTML documents based on CSS selectors. Trading reports, tester reports, your favorite economic calendars, public signals, account monitoring and additional online quote sources will become available straight from MQL.
The purpose of this article is to create a custom tool, which would enable users to receive and use the entire array of information about patterns discussed earlier. We will create a library of pattern related functions which you will be able to use in your own indicators, trading panels, Expert Advisors, etc.
Comprehensive data processing requires extensive tools and is often beyond the sandbox of one single application. Specialized programming languages are used for processing and analyzing data, statistics and machine learning. One of the leading programming languages for data processing is Python. The article provides a description of how to connect MetaTrader 5 and Python using sockets, as well as how to receive quotes via the terminal API.
In the first part of the article, I have described a modified ZigZag indicator and a class for receiving data of that type of indicators. Here, I will show how to develop indicators based on these tools and write an EA for tests that features making deals according to signals formed by ZigZag indicator. As an addition, the article will introduce a new version of the EasyAndFast library for developing graphical user interfaces.
Many researchers do not pay enough attention to determining the price behavior. At the same time, complex methods are used, which very often are simply “black boxes”, such as machine learning or neural networks. The most important question arising in that case is what data to submit for training a particular model.
In the article, we will apply Reinforcement learning to develop self-learning Expert Advisors. In the previous article, we considered the Random Decision Forest algorithm and wrote a simple self-learning EA based on Reinforcement learning. The main advantages of such an approach (trading algorithm development simplicity and high "training" speed) were outlined. Reinforcement learning (RL) is easily incorporated into any trading EA and speeds up its optimization.
Based on universal tools designed for working with Kohonen networks, we construct the system of analyzing and selecting the optimal EA parameters and consider forecasting time series. In Part I, we corrected and improved the publicly available neural network classes, having added necessary algorithms. Now, it is time to apply them to practice.
In this article we will consider in detail the martingale system. We will review whether this system can be applied in trading and how to use it in order to minimize risks. The main disadvantage of this simple system is the probability of losing the entire deposit. This fact must be taken into account, if you decide to trade using the martingale technique.
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.
The article considers applying the separate optimization method during various market conditions. Separate optimization means defining trading system's optimal parameters by optimizing for an uptrend and downtrend separately. To reduce the effect of false signals and improve profitability, the systems are made flexible, meaning they have some specific set of settings or input data, which is justified because the market behavior is constantly changing.
The article describes the creation of a custom exchange symbol using the MQL5 language. In particular, it considers the use of exchange quotes from the popular Finam website. Another option considered in this article is the possibility to work with an arbitrary format of text files used in the creation of the custom symbol. This allows working with any financial symbols and data sources. After creating a custom symbol, we can use all the capabilities of the MetaTrader 5 Strategy Tester to test trading algorithms for exchange instruments.
The article describes the algorithm for implementing the OpenCL candlestick patterns tester in the "1 minute OHLC" mode. We will also compare its speed with the built-in strategy tester launched in the fast and slow optimization modes.
The article describes the library allowing you to increase the efficiency of working with HTTP requests in MQL5. Execution of WebRequest in non-blocking mode is implemented in additional threads that use auxiliary charts and Expert Advisors, exchanging custom events and reading shared resources. The source codes are applied as well.
This is the last article within the series devoted to the Reversing trading strategy. Here we will try to solve the problem, which caused the testing results instability in previous articles. We will also develop and test our own algorithm for manual trading in any market using the reversing strategy.
In this article, we continue to dwell on reversing techniques. We will try to reduce the maximum balance drawdown till an acceptable level for the instruments considered earlier. We will see if the measures will reduce the profit. We will also check how the reversing method performs on other markets, including stock, commodity, index, ETF and agricultural markets. Attention, the article contains a lot of images!
This article is a follow-up to the previous one called "Reversal patterns: Testing the Double top/bottom pattern". Now we will have a look at another well-known reversal pattern called Head and Shoulders, compare the trading efficiency of the two patterns and make an attempt to combine them into a single trading system.
