Articles on machine learning in trading

There are many posts in the MQL5 Forum asking for help calculating the slope of price changes. This article will demonstrate one possible way of calculating the angle formed by the changes in price in any market you wish to trade. Additionally, we will answer if engineering this new feature is worth the extra effort and time invested. We will explore if the slope of the price can improve any of our AI model's accuracy when forecasting the USDZAR pair on the M1.

In this article, we will explore and implement, methods for assessing model quality that utilize a single dataset as both training and validation sets.

In this article, we discuss and demonstrate how to convert nominal predictors into numerical formats that are suitable for machine learning algorithms, using both Python and MQL5.

Traditional machine learning teaches practitioners to be vigilant not to overfit their models. However, this ideology is being challenged by new insights published by diligent researches from Harvard, who have discovered that what appears to be overfitting may in some circumstances be the results of terminating your training procedures prematurely. We will demonstrate how we can use the ideas published in the research paper, to improve our use of AI in forecasting market returns.

The article is devoted to the AMO algorithm, which models the seasonal migration of animals in search of optimal conditions for life and reproduction. The main features of AMO include the use of topological neighborhood and a probabilistic update mechanism, which makes it easy to implement and flexible for various optimization tasks.

Support Vector Machines classify data based on predefined classes by exploring the effects of increasing its dimensionality. It is a supervised learning method that is fairly complex given its potential to deal with multi-dimensioned data. For this article we consider how it’s very basic implementation of 2-dimensioned data can be done more efficiently with Newton’s Polynomial when classifying price-action.

The article discusses the Tabu Search algorithm, one of the first and most well-known metaheuristic methods. We will go through the algorithm operation in detail, starting with choosing an initial solution and exploring neighboring options, with an emphasis on using a tabu list. The article covers the key aspects of the algorithm and its features.

The article considers a group of optimization algorithms known as Evolution Strategies (ES). They are among the very first population algorithms to use evolutionary principles for finding optimal solutions. We will implement changes to the conventional ES variants and revise the test function and test stand methodology for the algorithms.

Spatial Temporal Fusion which is using both ‘space’ and time metrics in modelling data is primarily useful in remote-sensing, and a host of other visual based activities in gaining a better understanding of our surroundings. Thanks to a published paper, we take a novel approach in using it by examining its potential to traders.

NumPy library is powering almost all the machine learning algorithms to the core in Python programming language, In this article we are going to implement a similar module which has a collection of all the complex code to aid us in building sophisticated models and algorithms of any kind.

We will consider the principle of constructing multi-population algorithms. As an example of this type of algorithm, we will have a look at the new custom algorithm - Evolution of Social Groups (ESG). We will analyze the basic concepts, population interaction mechanisms and advantages of this algorithm, as well as examine its performance in optimization problems.

This is a continuation of the previous article considering the idea of social groups. The article explores the evolution of social groups using movement and memory algorithms. The results will help to understand the evolution of social systems and apply them in optimization and search for solutions.

By studying the FEDformer method, we opened the door to the frequency domain of time series representation. In this new article, we will continue the topic we started. We will consider a method with which we can not only conduct an analysis, but also predict subsequent states in a particular area.

In this article, we present the implementation of several ensemble learning methods in MQL5 and examine their effectiveness across different scenarios.

This article explores a feature selection algorithm introduced in the paper 'Local Feature Selection for Data Classification' by Narges Armanfard et al. The algorithm is implemented in Python to build binary classifier models that can be integrated with MetaTrader 5 applications for inference.

SARSA, which is an abbreviation for State-Action-Reward-State-Action is another algorithm that can be used when implementing reinforcement learning. So, as we saw with Q-Learning and DQN, we look into how this could be explored and implemented as an independent model rather than just a training mechanism, in wizard assembled Expert Advisors.

This article is somewhat different from my earlier publications. In this article, we will talk about an alternative representation of time series. Piecewise linear representation of time series is a method of approximating a time series using linear functions over small intervals.

We continue our last article on DDPG with MA and stochastic indicators by examining other key Reinforcement Learning classes crucial for implementing DDPG. Though we are mostly coding in python, the final product, of a trained network will be exported to as an ONNX to MQL5 where we integrate it as a resource in a wizard assembled Expert Advisor.

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.

Temporal Difference is another algorithm in reinforcement learning that updates Q-Values basing on the difference between predicted and actual rewards during agent training. It specifically dwells on updating Q-Values without minding their state-action pairing. We therefore look to see how to apply this, as we have with previous articles, in a wizard assembled Expert Advisor.

In this article we are creating a synthetic symbol using a Generative Adversarial Network (GAN) involves generating realistic Financial data that mimics the behavior of actual market instruments, such as EURUSD. The GAN model learns patterns and volatility from historical market data and creates synthetic price data with similar characteristics.

The article considers an optimization method based on the principles of the body's immune system - Micro Artificial Immune System (Micro-AIS) - a modification of AIS. Micro-AIS uses a simpler model of the immune system and simple immune information processing operations. The article also discusses the advantages and disadvantages of Micro-AIS compared to conventional AIS.

We continue to discuss the family of Decision Transformer methods. From previous article, we have already noticed that training the transformer underlying the architecture of these methods is a rather complex task and requires a large labeled dataset for training. In this article we will look at an algorithm for using unlabeled trajectories for preliminary model training.

In today's discussion, we examine the strategy of multiple time-frame analysis to learn on which time frame our AI model performs best. Our analysis leads us to conclude that the Monthly and Hourly time-frames produce models with relatively low error rates on the EURUSD pair. We used this to our advantage and created a trading algorithm that makes AI predictions on the Monthly time frame, and executes its trades on the Hourly time frame.

Effective identification and preservation of the local structure of market data in noisy conditions is a critical task in trading. The use of the Self-Attention mechanism has shown promising results in processing such data; however, the classical approach does not account for the local characteristics of the underlying structure. In this article, I introduce an algorithm capable of incorporating these structural dependencies.

Symbolic Regression is a form of regression that starts with minimal to no assumptions on what the underlying model that maps the sets of data under study would look like. Even though it can be implemented by Bayesian Methods or Neural Networks, we look at how an implementation with Genetic Algorithms can help customize an expert signal class usable in the MQL5 wizard.

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.

The article reveals the potential of the ANS algorithm as an important step in the development of flexible and intelligent optimization methods that can take into account the specifics of the problem and the dynamics of the environment in the search space.

In a world overflowing with noisy and unpredictable data, identifying meaningful patterns can be challenging. In this article, we'll explore seasonal decomposition, a powerful analytical technique that helps separate data into its key components: trend, seasonal patterns, and noise. By breaking data down this way, we can uncover hidden insights and work with cleaner, more interpretable information.

In this article, we will talk about algorithms for using attention methods in solving problems of detecting objects in a point cloud. Object detection in point clouds is important for many real-world applications.

Replay buffers in Reinforcement Learning are particularly important with off-policy algorithms like DQN or SAC. This then puts the spotlight on the sampling process of this memory-buffer. While default options with SAC, for instance, use random selection from this buffer, Prioritized Experience Replay buffers fine tune this by sampling from the buffer based on a TD-score. We review the importance of Reinforcement Learning, and, as always, examine just this hypothesis (not the cross-validation) in a wizard assembled Expert Advisor.

In this article, we will look at the theory of causal inference using machine learning, as well as the custom approach implementation in Python. Causal inference and causal thinking have their roots in philosophy and psychology and play an important role in our understanding of reality.