Articles on machine learning in trading

In recent articles, we have seen several options for using the Decision Transformer method. The method allows analyzing not only the current state, but also the trajectory of previous states and actions performed in them. In this article, we will focus on using this method in hierarchical models.

Dive into the heart of Artificial Intelligence's enigma as we navigate the tumultuous waters of explainability. In a realm where models conceal their inner workings, our exploration unveils the "disagreement problem" that echoes through the corridors of machine learning.

During the offline learning, we optimize the Agent's policy based on the training sample data. The resulting strategy gives the Agent confidence in its actions. However, such optimism is not always justified and can cause increased risks during the model operation. Today we will look at one of the methods to reduce these risks.

The article considers the theoretical application of quantization in the construction of tree models and showcases the implemented quantization methods in CatBoost. No complex mathematical equations are used.

Data formats used to represent machine learning models play a crucial role in their effectiveness. In recent years, several new types of data have emerged, specifically designed for working with deep learning models. In this article, we will focus on two new data formats that have become widely adopted in modern models.

Examples of passing indicators to a perceptron. The article describes general concepts and showcases the simplest ready-made Expert Advisor followed by the results of its optimization and forward test.

The last two articles were devoted to the Decision Transformer method, which models action sequences in the context of an autoregressive model of desired rewards. In this article, we will look at another optimization algorithm for this method.

Uncover the secrets behind these powerful dimensionality reduction techniques as we dissect their applications within the MQL5 trading environment. Delve into the nuances of Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA), gaining a profound understanding of their impact on strategy development and market analysis.

In the previous article, we got acquainted with the Decision Transformer. But the complex stochastic environment of the foreign exchange market did not allow us to fully implement the potential of the presented method. In this article, I will introduce an algorithm that is aimed at improving the performance of algorithms in stochastic environments.

Unlock the secrets of MQL5 programming in our latest article! Delve into the essentials of structures, classes, and time functions, empowering your coding journey. Whether you're a beginner or an experienced developer, our guide simplifies complex concepts, providing valuable insights for mastering MQL5. Elevate your programming skills and stay ahead in the world of algorithmic trading!

The article discusses Stochastic Diffusion Search (SDS), which is a very powerful and efficient optimization algorithm based on the principles of random walk. The algorithm allows finding optimal solutions in complex multidimensional spaces, while featuring a high speed of convergence and the ability to avoid local extrema.

We continue to explore reinforcement learning methods. In this article, I will focus on a slightly different algorithm that considers the Agent’s policy in the paradigm of constructing a sequence of actions.

The article considers the algorithm of the MEC family called the simple mind evolutionary computation algorithm (Simple MEC, SMEC). The algorithm is distinguished by the beauty of its idea and ease of implementation.

Number Walls are a variant of Linear Shift Back Registers that prescreen sequences for predictability by checking for convergence. We look at how these ideas could be of use in MQL5.

The article presents a detailed description of the shuffled frog-leaping (SFL) algorithm and its capabilities in solving optimization problems. The SFL algorithm is inspired by the behavior of frogs in their natural environment and offers a new approach to function optimization. The SFL algorithm is an efficient and flexible tool capable of processing a variety of data types and achieving optimal solutions.

AdaBoost, a powerful boosting algorithm designed to elevate the performance of your AI models. AdaBoost, short for Adaptive Boosting, is a sophisticated ensemble learning technique that seamlessly integrates weak learners, enhancing their collective predictive strength.

Here I will consider the fairly new Stochastic Marginal Actor-Critic (SMAC) algorithm, which allows building latent variable policies within the framework of entropy maximization.

Embark on an illuminating journey with Part Two of our MQL5 series. These articles are not just tutorials, they're doorways to an enchanted realm where programming novices and wizards alike unite. What makes this journey truly magical? Part Two of our MQL5 series stands out with its refreshing simplicity, making complex concepts accessible to all. Engage with us interactively as we answer your questions, ensuring an enriching and personalized learning experience. Let's build a community where understanding MQL5 is an adventure for everyone. Welcome to the enchantment!

This series of articles introduces several time series labeling methods, which can create data that meets most artificial intelligence models, and targeted data labeling according to needs can make the trained artificial intelligence model more in line with the expected design, improve the accuracy of our model, and even help the model make a qualitative leap!

Machine learning models are difficult to interpret and understanding why our models deviate from our expectations is critical if we want to gain any value from using such advanced techniques. Without comprehensive insight into the inner workings of our model, we might fail to spot bugs that are corrupting our model's performance, we may waste time over engineering features that aren't predictive and in the long run we risk underutilizing the power of these models. Fortunately, there is a sophisticated and well maintained all in one solution that allows us to see exactly what our model is doing underneath the hood.

The study of the environment in reinforcement learning is a pressing problem. We have already looked at some approaches previously. In this article, we will have a look at yet another method based on maximizing the nuclear norm. It allows agents to identify environmental states with a high degree of novelty and diversity.

Discover the secrets of algorithmic alchemy as we guide you through the blend of artistry and precision in decoding financial landscapes. Unearth how Random Forests transform data into predictive prowess, offering a unique perspective on navigating the complex terrain of stock markets. Join us on this journey into the heart of financial wizardry, where we demystify the role of Random Forests in shaping market destiny and unlocking the doors to lucrative opportunities

K-Means clustering takes the approach to grouping data points as a process that’s initially focused on the macro view of a data set that uses random generated cluster centroids before zooming in and adjusting these centroids to accurately represent the data set. We will look at this and exploit a few of its use cases.

Whenever we consider reinforcement learning methods, we are faced with the issue of efficiently exploring the environment. Solving this issue often leads to complication of the algorithm and training of additional models. In this article, we will look at an alternative approach to solving this problem.

Perceptrons, single hidden layer networks, can be a good segue for anyone familiar with basic automated trading and is looking to dip into neural networks. We take a step by step look at how this could be realized in a signal class assembly that is part of the MQL5 Wizard classes for expert advisors.

We have already talked more than once about the importance of correctly selecting the reward function, which we use to stimulate the desired behavior of the Agent by adding rewards or penalties for individual actions. But the question remains open about the decryption of our signals by the Agent. In this article, we will talk about reward decomposition in terms of transmitting individual signals to the trained Agent.