In this article, I would like to introduce you to a new complex timeseries forecasting method, which harmoniously combines the advantages of linear models and transformers.
We already know that pre-processing of the input data plays a major role in the stability of model training. To process "raw" input data online, we often use a batch normalization layer. But sometimes we need a reverse procedure. In this article, we discuss one of the possible approaches to solving this problem.
In the second part of the article, we will move on to the practical implementation of the BSO algorithm, conduct tests on test functions and compare the efficiency of BSO with other optimization methods.
This article introduces the Conformer algorithm originally developed for the purpose of weather forecasting, which in terms of variability and capriciousness can be compared to financial markets. Conformer is a complex method. It combines the advantages of attention models and ordinary differential equations.
This article presents a comprehensive guide to implementing a sophisticated trading system using Causality Network Analysis (CNA) and Vector Autoregression (VAR) in MQL5. It covers the theoretical background of these methods, provides detailed explanations of key functions in the trading algorithm, and includes example code for implementation.
Support Vector Regression is an idealistic way of finding a function or ‘hyper-plane’ that best describes the relationship between two sets of data. We attempt to exploit this in time series forecasting within custom classes of the MQL5 wizard.
In this article, we will look at an innovative optimization method called BSO (Brain Storm Optimization) inspired by a natural phenomenon called "brainstorming". We will also discuss a new approach to solving multimodal optimization problems the BSO method applies. It allows finding multiple optimal solutions without the need to pre-determine the number of subpopulations. We will also consider the K-Means and K-Means++ clustering methods.
Since the goal here is didactic, we will proceed as simply as possible. That is, we will implement only what we need: matrix multiplication. You will see today that this is enough to simulate matrix-scalar multiplication. The most significant difficulty that many people encounter when implementing code using matrix factorization is this: unlike scalar factorization, where in almost all cases the order of the factors does not change the result, this is not the case when using matrices.
In the world of big data, there are millions of alternative datasets that hold the potential to enhance our trading strategies. In this series of articles, we will help you identify the most informative public datasets.
As already explained in the theoretical part, when working with neural networks we need to use linear regressions and derivatives. Why? The reason is that linear regression is one of the simplest formulas in existence. Essentially, linear regression is just an affine function. However, when we talk about neural networks, we are not interested in the effects of direct linear regression. We are interested in the equation that generates this line. We are not that interested in the line created. Do you know the main equation that we need to understand? If not, I recommend reading this article to understanding it.
Restricted Boltzmann Machines are a form of neural network that was developed in the mid 1980s at a time when compute resources were prohibitively expensive. At its onset, it relied on Gibbs Sampling and Contrastive Divergence in order to reduce dimensionality or capture the hidden probabilities/properties over input training data sets. We examine how Backpropagation can perform similarly when the RBM ‘embeds’ prices for a forecasting Multi-Layer-Perceptron.
In this series of articles, we revisit classic strategies to see if we can improve them using AI. In today's article, we will examine the popular strategy of multiple time-frame analysis to judge if the strategy would be enhanced with AI.
In our series on integrating MQL5 with data processing packages, we delve in to the powerful combination of machine learning and predictive analysis. We will explore how to seamlessly connect MQL5 with popular machine learning libraries, to enable sophisticated predictive models for financial markets.
The article explores the bird swarm-based algorithm (BSA) inspired by the collective flocking interactions of birds in nature. The different search strategies of individuals in BSA, including switching between flight, vigilance and foraging behavior, make this algorithm multifaceted. It uses the principles of bird flocking, communication, adaptability, leading and following to efficiently find optimal solutions.
In this series of articles, we revisit classical strategies to see if we can improve the strategy using AI. In today's article, we will examine a popular strategy of multiple symbol analysis using a basket of correlated securities, we will focus on the exotic USDZAR currency pair.
Regularization is a form of penalizing the loss function in proportion to the discrete weighting applied throughout the various layers of a neural network. We look at the significance, for some of the various regularization forms, this can have in test runs with a wizard assembled Expert Advisor.
In this series of articles, we analyze classical trading strategies using modern algorithms to determine whether we can improve the strategy using AI. In today's article, we revisit a classical approach for trading the SP500 using the relationship it has with US Treasury Notes.
The article considers Boids algorithm based on unique examples of animal flocking behavior. In turn, the Boids algorithm serves as the basis for the creation of the whole class of algorithms united under the name "Swarm Intelligence".
Developing a trading robot based on machine learning: A detailed guide. The first article in the series deals with collecting and preparing data and features. The project is implemented using the Python programming language and libraries, as well as the MetaTrader 5 platform.
This article presents a sophisticated Expert Advisor for forex trading, combining machine learning with technical analysis. It focuses on trading Apple stock, featuring adaptive optimization, risk management, and multiple strategies. Backtesting shows promising results with high profitability but also significant drawdowns, indicating potential for further refinement.
Loss Function is the key metric of machine learning algorithms that provides feedback to the training process by quantifying how well a given set of parameters are performing when compared to their intended target. We explore the various formats of this function in an MQL5 custom wizard class.
With the rapid development of artificial intelligence today, language models (LLMs) are an important part of artificial intelligence, so we should think about how to integrate powerful LLMs into our algorithmic trading. For most people, it is difficult to fine-tune these powerful models according to their needs, deploy them locally, and then apply them to algorithmic trading. This series of articles will take a step-by-step approach to achieve this goal.
In this article, we dive deep into the crucial aspects of choosing the most relevant and high-quality Forex data to enhance the performance of AI models.
Clustering algorithms in machine learning are important unsupervised learning algorithms that can divide the original data into groups with similar observations. By using these groups, you can analyze the market for a specific cluster, search for the most stable clusters using new data, and make causal inferences. The article proposes an original method for time series clustering in Python.
Batch normalization is the pre-processing of data before it is fed into a machine learning algorithm, like a neural network. This is always done while being mindful of the type of Activation to be used by the algorithm. We therefore explore the different approaches that one can take in reaping the benefits of this, with the help of a wizard assembled Expert Advisor.
Integration enables seamless workflow where raw financial data from MQL5 can be imported into data processing packages like Jupyter Lab for advanced analysis including statistical testing.
Machine learning models come with various adjustable parameters. In this series of articles, we will explore how to customize your AI models to fit your specific market using the SciPy library.
It is a common practice for many Artificial Intelligence models to predict a single future value. However, in this article, we will delve into the powerful technique of using machine learning models to predict multiple future values. This approach, known as multistep forecasting, allows us to predict not only tomorrow's closing price but also the day after tomorrow's and beyond. By mastering multistep forecasting, traders and data scientists can gain deeper insights and make more informed decisions, significantly enhancing their predictive capabilities and strategic planning.
In this article, we will look at the Mersenne Twister random number generator and compare it with the standard one in MQL5. We will also find out the influence of the random number generator quality on the results of optimization algorithms.
In this series article, we will empirically analyze classic trading strategies to see if we can improve them using AI. In today's discussion, we tried to predict higher highs and lower lows using the Linear Discriminant Analysis model.
In previous works, we always assessed the current state of the environment. At the same time, the dynamics of changes in indicators always remained "behind the scenes". In this article I want to introduce you to an algorithm that allows you to evaluate the direct change in data between 2 successive environmental states.
We wrap up our look at learning rate sensitivity to the performance of Expert Advisors by primarily examining the Adaptive Learning Rates. These learning rates aim to be customized for each parameter in a layer during the training process and so we assess potential benefits vs the expected performance toll.
Whale Optimization Algorithm (WOA) is a metaheuristic algorithm inspired by the behavior and hunting strategies of humpback whales. The main idea of WOA is to mimic the so-called "bubble-net" feeding method, in which whales create bubbles around prey and then attack it in a spiral motion.
In this article, I will get acquainted with the GTGAN algorithm, which was introduced in January 2024 to solve complex problems of generation architectural layouts with graph constraints.
Here we will dive into the world of hybridization of optimization algorithms by looking at three key types: strategy mixing, sequential and parallel hybridization. We will conduct a series of experiments combining and testing relevant optimization algorithms.
Convolutional Neural Networks (CNNs) are renowned for their prowess in detecting patterns in images and videos, with applications spanning diverse fields. In this article, we explore the potential of CNNs to identify valuable patterns in financial markets and generate effective trading signals for MetaTrader 5 trading bots. Let us discover how this deep machine learning technique can be leveraged for smarter trading decisions.
The Learning Rate, is a step size towards a training target in many machine learning algorithms’ training processes. We examine the impact its many schedules and formats can have on the performance of a Generative Adversarial Network, a type of neural network that we had examined in an earlier article.
We continue our experiment that aims to examine the behavior of population optimization algorithms in the context of their ability to efficiently escape local minima when population diversity is low and reach global maxima. Research results are provided.
In the previous article, we discussed a simple RNN which despite its inability to understand long-term dependencies in the data, was able to make a profitable strategy. In this article, we are discussing both the Long-Short Term Memory(LSTM) and the Gated Recurrent Unit(GRU). These two were introduced to overcome the shortcomings of a simple RNN and to outsmart it.