Search

This article presents a novel approach to cryptocurrency price forecasting, leveraging advanced machine-learning techniques. By comparing traditional autoregressive models with recurrent neural network approaches, the study aims to evaluate the forecasting accuracy of Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models across various cryptocurrencies, including Bitcoin, Ethereum, Dogecoin, Polygon, and Toncoin. The data for this empirical study was sourced from historical prices of these specific cryptocurrencies, as recorded on the CoinMarketCap platform, covering January 2022 to April 2024. The methodology employed involves rigorous statistical and neural network modelling where each model's parameters were meticulously optimized for the specific characteristics of each cryptocurrency's price data. Performance metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) were used to assess the precision of each model. The main results indicate that LSTM and GRU models, leveraging deep learning techniques, generally outperformed the traditional ARIMA and SARIMA models regarding error metrics. This demonstrates a higher efficacy of neural networks in handling the non-linear complexities and volatile nature of cryptocurrency price movements. This study contributes to the ongoing discourse in financial technology by elucidating the practical implications of using advanced machine-learning techniques for economic forecasting. Importantly, it provides valuable insights that can directly inform and enhance the decision-making processes of investors and traders in digital assets.

Karamzin Island (the Peter the Great Bay, the East Sea) is the only nesting point of streaked shearwaters in Russian Federation. To understand and determine distribution patterns of streaked shearwaters along the Eastern Sea waters during nesting period, the Trackers WT-300 were set to 10 adult birds. Over the observation period (from 5 July 2016 to 7 January 2017), 4812 locations were registered. Analysis of data obtained revealed that main feeding points of colony studied were situated in the Peter the Great Bay along 50 m isobath and, to the less extension, near the eastern coast of Korean Peninsula. It was determined that streaked shearwaters most frequently visited waters with circular flows or zones of junctions of multidirectional flow. It was also shown that these zones had high concentrations of zooplankton.

The structure of this work in the field of queuing theory consists of two stages. The first stage presents Little’s Law in Multiphase Systems (MSs). To obtain this result, the Strong Law of Large Numbers (SLLN)-type theorems for the most important MS probability characteristics (i.e., queue length of jobs and virtual waiting time of a job) are proven. The next stage of the work is to verify the result obtained in the first stage.

Darbo tikslas yra įvertinti įvairias investavimo strategijas pagal jų pelningumą realiose ir virtualiose fi nansų rinkose. Darbe aprašytas atnaujintas fi nansų rinkos modelis, analizuojami eksperimentinių skaičiavimų rezultatai. On the experimental investigation of investment strategies in the real and virtual fi nancial markets Jonas Mockus, Igor Katin, Joana Katina Summary The optimal fi nancial investment (Portfolio) problem was investigated by leading fi nancial organizations and scientists. The aim of these works was to defi ne the optimal diversifi cation of the assets depending on the acceptable risk level. The aim of the paper is to evaluate different investment strategies in the real and virtual fi nancial markets. This aim is the new element of the proposed simulation system since optimization is performed in the space of investment strategies; both daily and long-term. A number of different investment strategies are presented, including the ones based on the Modern Portfolio Theory (MPT). The simulated investment procedures include different prediction methods. The methods that minimize the mean absolute error (MAE) are added to the traditional ones that minimize the least squares error (MSE). The results of the virtual fi nancial market are compared with historical data. The model is designed as a tool to represent the behavior of an individual investor which wants to predict how the expected profi t depends on different investment strategies using different forecasting methods of real and virtual stocks.

In this paper, the updated model USEGM simulating the stock exchange is investigated. The updated model includes the transaction costs to reflect the reality better. To represent users that prefer linear utility functions, USEGM adds the new models which minimize absolute prediction errors to the traditional ones minimizing square deviations. However, the main objective of USEGM is not forecasting, but simulation of financial time series that are affected by predictions of the participants. The model has been compared with actual financial time series.

The objective of this work is to investigate experimentally the well-known autoregressive models as simplest algorithms simulating prediction processes of the stockholders using the historical stock rates only. The “virtual” stock exchange which applies these algorithms can help in testing various assumptions of investor behavior. To represent users that prefer linear utility functions, the autoregressive moving-average model (ARMA-ABS(p, q)), minimizing the absolute values of prediction errors is regarded, in addition to the traditional ARMA(p, q) model which minimize the least square errors. The results of two hundred actual financial time series and a hundred of virtual ones are discussed in short.