Add a new article
Self-adapting algorithm (Part IV): Additional functionality and tests
Self-adapting algorithm (Part IV): Additional functionality and tests
I continue filling the algorithm with the minimum necessary functionality and testing the results. The profitability is quite low but the articles demonstrate the model of the fully automated profitable trading on completely different instruments traded on fundamentally different markets.
Neural networks made easy (Part 11): A take on GPT
Neural networks made easy (Part 11): A take on GPT
Perhaps one of the most advanced models among currently existing language neural networks is GPT-3, the maximal variant of which contains 175 billion parameters. Of course, we are not going to create such a monster on our home PCs. However, we can view which architectural solutions can be used in our work and how we can benefit from them.
Self-adapting algorithm (Part III): Abandoning optimization
Self-adapting algorithm (Part III): Abandoning optimization
It is impossible to get a truly stable algorithm if we use optimization based on historical data to select parameters. A stable algorithm should be aware of what parameters are needed when working on any trading instrument at any time. It should not forecast or guess, it should know for sure.
Neural networks made easy (Part 10): Multi-Head Attention
Neural networks made easy (Part 10): Multi-Head Attention
We have previously considered the mechanism of self-attention in neural networks. In practice, modern neural network architectures use several parallel self-attention threads to find various dependencies between the elements of a sequence. Let us consider the implementation of such an approach and evaluate its impact on the overall network performance.
Finding seasonal patterns in the forex market using the CatBoost algorithm
Finding seasonal patterns in the forex market using the CatBoost algorithm
The article considers the creation of machine learning models with time filters and discusses the effectiveness of this approach. The human factor can be eliminated now by simply instructing the model to trade at a certain hour of a certain day of the week. Pattern search can be provided by a separate algorithm.
Neural networks made easy (Part 9): Documenting the work
Neural networks made easy (Part 9): Documenting the work
We have already passed a long way and the code in our library is becoming bigger and bigger. This makes it difficult to keep track of all connections and dependencies. Therefore, I suggest creating documentation for the earlier created code and to keep it updating with each new step. Properly prepared documentation will help us see the integrity of our work.
The market and the physics of its global patterns
The market and the physics of its global patterns
In this article, I will try to test the assumption that any system with even a small understanding of the market can operate on a global scale. I will not invent any theories or patterns, but I will only use known facts, gradually translating these facts into the language of mathematical analysis.
Developing a self-adapting algorithm (Part I): Finding a basic pattern
Developing a self-adapting algorithm (Part I): Finding a basic pattern
In the upcoming series of articles, I will demonstrate the development of self-adapting algorithms considering most market factors, as well as show how to systematize these situations, describe them in logic and take them into account in your trading activity. I will start with a very simple algorithm that will gradually acquire theory and evolve into a very complex project.
Neural networks made easy (Part 8): Attention mechanisms
Neural networks made easy (Part 8): Attention mechanisms
In previous articles, we have already tested various options for organizing neural networks. We also considered convolutional networks borrowed from image processing algorithms. In this article, I suggest considering Attention Mechanisms, the appearance of which gave impetus to the development of language models.
Manual charting and trading toolkit (Part II). Chart graphics drawing tools
Manual charting and trading toolkit (Part II). Chart graphics drawing tools
This is the next article within the series, in which I show how I created a convenient library for manual application of chart graphics by utilizing keyboard shortcuts. The tools used include straight lines and their combinations. In this part, we will view how the drawing tools are applied using the functions described in the first part. The library can be connected to any Expert Advisor or indicator which will greatly simplify the charting tasks. This solution DOES NOT use external dlls, while all the commands are implemented using built-in MQL tools.
Using spreadsheets to build trading strategies
Using spreadsheets to build trading strategies
The article describes the basic principles and methods that allow you to analyze any strategy using spreadsheets (Excel, Calc, Google). The obtained results are compared with MetaTrader 5 tester.
Neural networks made easy (Part 7): Adaptive optimization methods
Neural networks made easy (Part 7): Adaptive optimization methods
In previous articles, we used stochastic gradient descent to train a neural network using the same learning rate for all neurons within the network. In this article, I propose to look towards adaptive learning methods which enable changing of the learning rate for each neuron. We will also consider the pros and cons of this approach.
Gradient boosting in transductive and active machine learning
Gradient boosting in transductive and active machine learning
In this article, we will consider active machine learning methods utilizing real data, as well discuss their pros and cons. Perhaps you will find these methods useful and will include them in your arsenal of machine learning models. Transduction was introduced by Vladimir Vapnik, who is the co-inventor of the Support-Vector Machine (SVM).
Neural networks made easy (Part 6): Experimenting with the neural network learning rate
Neural networks made easy (Part 6): Experimenting with the neural network learning rate
We have previously considered various types of neural networks along with their implementations. In all cases, the neural networks were trained using the gradient decent method, for which we need to choose a learning rate. In this article, I want to show the importance of a correctly selected rate and its impact on the neural network training, using examples.
A scientific approach to the development of trading algorithms
A scientific approach to the development of trading algorithms
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.
Neural networks made easy (Part 5): Multithreaded calculations in OpenCL
Neural networks made easy (Part 5): Multithreaded calculations in OpenCL
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.
Neural networks made easy (Part 4): Recurrent networks
Neural networks made easy (Part 4): Recurrent networks
We continue studying the world of neural networks. In this article, we will consider another type of neural networks, recurrent networks. This type is proposed for use with time series, which are represented in the MetaTrader 5 trading platform by price charts.
Basic math behind Forex trading
Basic math behind Forex trading
The article aims to describe the main features of Forex trading as simply and quickly as possible, as well as share some basic ideas with beginners. It also attempts to answer the most tantalizing questions in the trading community along with showcasing the development of a simple indicator.
Brute force approach to pattern search
Brute force approach to pattern search
In this article, we will search for market patterns, create Expert Advisors based on the identified patterns, and check how long these patterns remain valid, if they ever retain their validity.
Parallel Particle Swarm Optimization
Parallel Particle Swarm Optimization
The article describes a method of fast optimization using the particle swarm algorithm. It also presents the method implementation in MQL, which is ready for use both in single-threaded mode inside an Expert Advisor and in a parallel multi-threaded mode as an add-on that runs on local tester agents.
Neural networks made easy (Part 3): Convolutional networks
Neural networks made easy (Part 3): Convolutional networks
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.
Price series discretization, random component and noise
Price series discretization, random component and noise
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.
Neural networks made easy (Part 2): Network training and testing
Neural networks made easy (Part 2): Network training and testing
In this second article, we will continue to study neural networks and will consider an example of using our created CNet class in Expert Advisors. We will work with two neural network models, which show similar results both in terms of training time and prediction accuracy.
What is a trend and is the market structure based on trend or flat?
What is a trend and is the market structure based on trend or flat?
Traders often talk about trends and flats but very few of them really understand what a trend/flat really is and even fewer are able to clearly explain these concepts. Discussing these basic terms is often beset by a solid set of prejudices and misconceptions. However, if we want to make profit, we need to understand the mathematical and logical meaning of these concepts. In this article, I will take a closer look at the essence of trend and flat, as well as try to define whether the market structure is based on trend, flat or something else. I will also consider the most optimal strategies for making profit on trend and flat markets.
On Methods to Detect Overbought/Oversold Zones. Part I
On Methods to Detect Overbought/Oversold Zones. Part I
Overbought/oversold zones characterize a certain state of the market, differentiating through weaker changes in the prices of securities. This adverse change in the synamics is pronounced most at the final stage in the development of trends of any scales. Since the profit value in trading depends directly on the capability of covering as large trend amplitude as possible, the accuracy of detecting such zones is a key task in trading with any securities whatsoever.
Practical application of neural networks in trading. It's time to practice
Practical application of neural networks in trading. It's time to practice
The article provides a description and instructions for the practical use of neural network modules on the Matlab platform. It also covers the main aspects of creation of a trading system using the neural network module. In order to be able to introduce the complex within one article, I had to modify it so as to combine several neural network module functions in one program.
Applying the probability theory to trading gaps
Applying the probability theory to trading gaps
In this article, we will apply the probability theory and mathematical statistics methods to creating and testing trading strategies. We will also look for optimal trading risk using the differences between the price and the random walk. It is proved that if prices behave like a zero-drift random walk (with no directional trend), then profitable trading is impossible.
MQL5: Analysis and Processing of Commodity Futures Trading Commission (CFTC) Reports in MetaTrader 5
MQL5: Analysis and Processing of Commodity Futures Trading Commission (CFTC) Reports in MetaTrader 5
In this article, we will develop a tool for CFTC report analysis. We will solve the following problem: to develop an indicator, that allows using the CFTC report data directly from the data files provided by Commission without an intermediate processing and conversion. Further, it can be used for the different purposes: to plot the data as an indicator, to proceed with the data in the other indicators, in the scripts for the automated analysis, in the Expert Advisors for the use in the trading strategies.
Comparing different types of moving averages in trading
Comparing different types of moving averages in trading
This article deals with seven types of moving averages (MA) and a trading strategy to work with them. We also test and compare various MAs at a single trading strategy and evaluate the efficiency of each moving average compared to others.
Developing Pivot Mean Oscillator: a novel Indicator for the Cumulative Moving Average
Developing Pivot Mean Oscillator: a novel Indicator for the Cumulative Moving Average
This article presents Pivot Mean Oscillator (PMO), an implementation of the cumulative moving average (CMA) as a trading indicator for the MetaTrader platforms. In particular, we first introduce Pivot Mean (PM) as a normalization index for timeseries that computes the fraction between any data point and the CMA. We then build PMO as the difference between the moving averages applied to two PM signals. Some preliminary experiments carried out on the EURUSD symbol to test the efficacy of the proposed indicator are also reported, leaving ample space for further considerations and improvements.