Authors

Building and analyzing a machine learning model for short-term bitcoin market forecasting based on recurrent neural networks

In this article, the construction and analysis of machine learning models were performed for short-term forecasting in the cryptocurrency market on the example of bitcoin – one of the most popular cryptocurrencies in the world. The initial data for the study leads to the conclusion that over the long period of its existence, bitcoin has shown a high degree of volatility, especially evident in comparison with traditional financial instruments. The article substantiates that this market is influenced by a multitude of factors. No one can say for sure what makes up the value of a particular cryptocurrency, as it involves a range of reasons, which cannot be fully taken into account. To overcome this problem, we have considered the principle of recurrent neural network. It is described why networks with memory are better at making predictions on the time series than conventional autoregressive model and standard forward propagation networks. The initial data processing algorithm and transformation methods are defined. The sample was reduced in order to increase the speed of the network, by reducing the number of recalculations of weights. The algorithm of the family of recurrent neural networks was built and trained to test the hypothesis about their better adaptivity due to short-term and long-term memory. The model is evaluated on the test data representing the bitcoin exchange rate for 2021–2022, since this period is characterized by high volatility. It is concluded that it is reasonable to use a similar type of models for short-term forecasting of cryptocurrency rates. Read more...

The method of preprocessing machine learning data for solving computer vision problems

In the field of machine learning, there is no single methodology for data preprocessing, since all stages of this process are unique for a specific task. However, a specific data type is used in each direction. The research hypothesis assumes that it is possible to clearly structure the sequences and phases of data preparation for text recognition tasks. The article discusses the basic principles of data preprocessing and the allocation of successive stages as a specific technique for the task of recognizing ABC characters. ETL set images were selected as the source data. Preprocessing included the stages of working with images, at each of which changes were made to the source data. The first step was cropping, which allowed to get rid of unnecessary information in the image. Next, the approach of converting the image to the original aspect ratio was considered and the method of converting from shades of gray to black and white format was determined. At the next stage, the character lines were artificially expanded for better recognition of printed alphabets. At the last stage of data preprocessing, augmentation was performed, which made it possible to better recognize ABC characters regardless of their position in space. As a result, the general structure of the data preprocessing methodology for text recognition tasks was built. Read more...