Articles on machine learning in trading

Hidden Markov Models (HMMs) are a powerful class of probabilistic models designed to analyze sequential data, where observed events depend on some sequence of unobserved (hidden) states that form a Markov process. The main assumptions of HMM include the Markov property for hidden states, meaning that the probability of transition to the next state depends only on the current state, and the independence of observations given knowledge of the current hidden state.

We continue to integrate methods proposed by the authors of the Attraos framework into trading models. Let me remind you that this framework uses concepts of chaos theory to solve time series forecasting problems, interpreting them as projections of multidimensional chaotic dynamic systems.

I present to you my new population optimization algorithm - Blood Inheritance Optimization (BIO), inspired by the human blood group inheritance system. In this algorithm, each solution has its own "blood type" that determines the way it evolves. Just as in nature where a child's blood type is inherited according to specific rules, in BIO new solutions acquire their characteristics through a system of inheritance and mutations.

We invite you to get acquainted with the DADA framework, which is an innovative method for detecting anomalies in time series. It helps distinguish random fluctuations from suspicious deviations. Unlike traditional methods, DADA is flexible and adapts to different data. Instead of a fixed compression level, it uses several options and chooses the most appropriate one for each case.

The article describes hierarchical training models that offer an effective approach to solving complex machine learning problems. Hierarchical models consist of several levels, each of which is responsible for different aspects of the task.

Do you want to know how to benefit from the difference in interest rates? This article considers how to use swap arbitrage in Forex to earn stable profit every night, creating a portfolio that is resistant to market fluctuations.

The quality of future state predictions plays an important role in the Goal-Conditioned Predictive Coding method, which we discussed in the previous article. In this article I want to introduce you to an algorithm that can significantly improve the prediction quality in stochastic environments, such as financial markets.

All the models we have considered so far analyze the state of the environment as a time sequence. However, the time series can also be represented in the form of frequency features. In this article, I introduce you to an algorithm that uses frequency components of a time sequence to predict future states.

In this article we will talk about using space-time transformations to effectively predict upcoming price movement. To improve the numerical prediction accuracy in STNN, a continuous attention mechanism is proposed that allows the model to better consider important aspects of the data.

When we use models to analyze the market situation, we mainly focus on the candlestick. However, it has long been known that candlestick patterns can help in predicting future price movements. In this article, we will get acquainted with a method that allows us to integrate both of these approaches.

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.

Eagle Strategy is an algorithm that mimics the eagle's two-phase hunting strategy: global search via Levy flights using Mantegna method, alternating with intense local exploitation using the firefly algorithm, a mathematically sound approach to balancing exploration and exploitation, and a bioinspired concept that combines two natural phenomena into a single computational method.

In this article, we introduce a method for segmenting 3D objects based on Superpoint Transformer (SPFormer), which eliminates the need for intermediate data aggregation. This speeds up the segmentation process and improves the performance of the model.

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.

We continue to build the algorithms that form the basis of the DADA framework, which is an advanced tool for detecting anomalies in time series. This approach enables effective distinguishing random fluctuations from significant deviations. Unlike classical methods, DADA dynamically adapts to different data types, choosing the optimal compression level in each specific case.

As a result of tests performed in previous articles, we came to the conclusion that the optimality of the trained strategy largely depends on the training set used. In this article, we will get acquainted with a fairly simple yet effective method for selecting trajectories to train models.

In this article we continue with our theme in the last of tackling everyday trading indicators viewed in a ‘new’ light. We are handling horizontal composition of natural transformations for this piece and the best indicator for this, that expands on what we just covered, is the double exponential moving average (DEMA).

The Simulated Annealing algorithm is a metaheuristic inspired by the metal annealing process. In the article, we will conduct a thorough analysis of the algorithm and debunk a number of common beliefs and myths surrounding this widely known optimization method. The second part of the article will consider the custom Simulated Isotropic Annealing (SIA) algorithm.

The article presents a new metaheuristic algorithm, Chaos Game Optimization (CGO), which demonstrates a unique ability to maintain high efficiency when dealing with high-dimensional problems. Unlike most optimization algorithms, CGO not only does not lose, but sometimes even increases performance when scaling a problem, which is its key feature.

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.

Time series forecasting in trading has evolved from traditional statistical models (like ARIMA) to deep learning approaches, but both require heavy tuning and training. Inspired by advances in NLP, Google’s TimesFM introduces a pretrained “foundation model” for time series that can perform strong forecasts even without task-specific training. For traders, this is powerful because it can be efficiently fine-tuned on their own data using lightweight methods like LoRA, reducing overfitting while adapting to changing market conditions.

In this article, we will look at the Comet Tail Optimization Algorithm (CTA), which draws inspiration from unique space objects - comets and their impressive tails that form when approaching the Sun. The algorithm is based on the concept of the motion of comets and their tails, and is designed to find optimal solutions in optimization problems.

In this article, we will continue exploring the Artificial Bee Hive Algorithm (ABHA) by diving into the code and considering the remaining methods. As you might remember, each bee in the model is represented as an individual agent whose behavior depends on internal and external information, as well as motivational state. We will test the algorithm on various functions and summarize the results by presenting them in the rating table.

In this article, we will take a quick look at some methods to get a function that can represent our data in the database. I will not go into detail about how to use statistics and probability studies to interpret the results. Let's leave that for those who really want to delve into the mathematical side of the matter. Exploring these questions will be critical to understanding what is involved in studying neural networks. Here we will consider this issue quite calmly.

We continue to explore the analysis and forecasting of time series in the frequency domain. In this article, we will get acquainted with a new method to forecast data in the frequency domain, which can be added to many of the algorithms we have studied previously.

The article presents a comprehensive analysis of the Coral Reef Optimization (CRO) algorithm, a metaheuristic method inspired by the biological processes of coral reef formation and development. The algorithm models key aspects of coral evolution: broadcast spawning, brooding, larval settlement, asexual reproduction, and competition for limited reef space. Particular attention is paid to the improved version of the algorithm.

The article presents the Big Bang - Big Crunch method, which has two key phases: cyclic generation of random points and their compression to the optimal solution. This approach combines exploration and refinement, allowing us to gradually find better solutions and open up new optimization opportunities.

In this article, we will get acquainted with an interesting algorithm that is built at the intersection of supervised and reinforcement learning methods.

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 the previous last article within this series, we looked at the Atom-Motif Contrastive Transformer (AMCT) framework, which uses contrastive learning to discover key patterns at all levels, from basic elements to complex structures. In this article, we continue implementing AMCT approaches using MQL5.

Generative Adversarial Networks are a pairing of Neural Networks that train off of each other for more accurate results. We adopt the conditional type of these networks as we look to possible application in forecasting Financial time series within an Expert Signal Class.

News drives the financial markets, especially major releases like Non-Farm Payrolls (NFPs). We've all witnessed how a single headline can trigger sharp price movements. In this article, we dive into the powerful intersection of news data and Artificial Intelligence.

The article focuses on creating a trading system with a real quantum simulator instead of mathematical analogies. The system uses 3 virtual qubits, quantum gates and superposition principles to analyze markets. It is implemented as a trading EA for MetaTrader 5 in MQL5. The main achievement is the transition from simulation to real quantum principles of financial information processing.

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.

The article considers an interesting algorithm derived from inanimate nature - intelligent water drops (IWD) simulating the process of river bed formation. The ideas of this algorithm made it possible to significantly improve the previous leader of the rating - SDS. As usual, the new leader (modified SDSm) can be found in the attachment.

As the model is trained based on the experience reproduction buffer, the current Actor policy moves further and further away from the stored examples, which reduces the efficiency of training the model as a whole. In this article, we will look at the algorithm of improving the efficiency of using samples in reinforcement learning algorithms.