Forecasting the cryptocurrency exchange rate based on the ranking of expert opinions
To date, most existing cryptocurrency exchanges do not have in their arsenal tools that would allow them to verify and investigate the information disseminated on social networks regarding a particular cryptocurrency. This makes it possible to conduct a relevant research with the subsequent develop...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Kharkiv National University of Radio Electronics
2023-12-01
|
Series: | Сучасний стан наукових досліджень та технологій в промисловості |
Subjects: | |
Online Access: | https://www.itssi-journal.com/index.php/ittsi/article/view/438 |
_version_ | 1797318080516325376 |
---|---|
author | Олена Гавриленко Михайло Мягкий |
author_facet | Олена Гавриленко Михайло Мягкий |
author_sort | Олена Гавриленко |
collection | DOAJ |
description |
To date, most existing cryptocurrency exchanges do not have in their arsenal tools that would allow them to verify and investigate the information disseminated on social networks regarding a particular cryptocurrency. This makes it possible to conduct a relevant research with the subsequent development of a tool that, if used correctly, will provide users with advisory advice on further actions in relation to the cryptocurrency under study in the system. Based on this advice, interested parties will be able to adjust their decisions regarding further financial steps. The basis of most recommender systems is always the need to identify some influencing factors, which are later given certain weights to facilitate and simplify the formulation of further advice for users. In this paper, we study the influence of celebrity publications on the formation of prices for a particular cryptocurrency at a certain point in time. The importance and existence of this influence was previously proven by statistical methods. The purpose of the study is to develop an algorithm for studying the level of influence of posts of each of the selected group of experts in social networks on the cryptocurrency rate. The object of the study is the forecast of cryptocurrency rates. The input data used were the list of experts whose level of influence will be studied, the time interval of the study, the number of posts made by each of the experts in question over the specified period of time, and the actual cryptocurrency rates for the relevant period. The experts were well-known personalities who are either knowledgeable in the field of finance in general and cryptocurrencies in particular, or whose activities are somehow related to a particular cryptocurrency. Research methods. Experts are ranked based on the full probability and Bayesian formulas. Forecasting of cryptocurrency rates in a selected period of time is carried out using the algorithm for forecasting cryptocurrency rates based on expert posts on social networks (ATAPSN). To control the accuracy of forecasts, the relative average error is calculated. Recommendations for financial transactions with cryptocurrencies are formed by entering the critical value of the exchange rate and calculating the arithmetic mean of cryptocurrency exchange rates for a specified period of time. Results. As a result of the research, an algorithm has been developed that allows taking into account the impact of the posts of each of the selected ranked group of experts on changes in the rates of a particular cryptocurrency. On the basis of the obtained forecasts, the paper presents a methodology for forming recommendations for financial transactions with them.
|
first_indexed | 2024-03-08T03:46:20Z |
format | Article |
id | doaj.art-db5e49be75594327be883a08508a2396 |
institution | Directory Open Access Journal |
issn | 2522-9818 2524-2296 |
language | English |
last_indexed | 2024-03-08T03:46:20Z |
publishDate | 2023-12-01 |
publisher | Kharkiv National University of Radio Electronics |
record_format | Article |
series | Сучасний стан наукових досліджень та технологій в промисловості |
spelling | doaj.art-db5e49be75594327be883a08508a23962024-02-09T17:55:31ZengKharkiv National University of Radio ElectronicsСучасний стан наукових досліджень та технологій в промисловості2522-98182524-22962023-12-014 (26)10.30837/ITSSI.2023.26.024Forecasting the cryptocurrency exchange rate based on the ranking of expert opinionsОлена Гавриленко0Михайло Мягкий1National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" To date, most existing cryptocurrency exchanges do not have in their arsenal tools that would allow them to verify and investigate the information disseminated on social networks regarding a particular cryptocurrency. This makes it possible to conduct a relevant research with the subsequent development of a tool that, if used correctly, will provide users with advisory advice on further actions in relation to the cryptocurrency under study in the system. Based on this advice, interested parties will be able to adjust their decisions regarding further financial steps. The basis of most recommender systems is always the need to identify some influencing factors, which are later given certain weights to facilitate and simplify the formulation of further advice for users. In this paper, we study the influence of celebrity publications on the formation of prices for a particular cryptocurrency at a certain point in time. The importance and existence of this influence was previously proven by statistical methods. The purpose of the study is to develop an algorithm for studying the level of influence of posts of each of the selected group of experts in social networks on the cryptocurrency rate. The object of the study is the forecast of cryptocurrency rates. The input data used were the list of experts whose level of influence will be studied, the time interval of the study, the number of posts made by each of the experts in question over the specified period of time, and the actual cryptocurrency rates for the relevant period. The experts were well-known personalities who are either knowledgeable in the field of finance in general and cryptocurrencies in particular, or whose activities are somehow related to a particular cryptocurrency. Research methods. Experts are ranked based on the full probability and Bayesian formulas. Forecasting of cryptocurrency rates in a selected period of time is carried out using the algorithm for forecasting cryptocurrency rates based on expert posts on social networks (ATAPSN). To control the accuracy of forecasts, the relative average error is calculated. Recommendations for financial transactions with cryptocurrencies are formed by entering the critical value of the exchange rate and calculating the arithmetic mean of cryptocurrency exchange rates for a specified period of time. Results. As a result of the research, an algorithm has been developed that allows taking into account the impact of the posts of each of the selected ranked group of experts on changes in the rates of a particular cryptocurrency. On the basis of the obtained forecasts, the paper presents a methodology for forming recommendations for financial transactions with them. https://www.itssi-journal.com/index.php/ittsi/article/view/438cryptocurrency exchange rate; forecasting algorithm; social media posts; ranking of a group of experts; information technology of intellectual analysis |
spellingShingle | Олена Гавриленко Михайло Мягкий Forecasting the cryptocurrency exchange rate based on the ranking of expert opinions Сучасний стан наукових досліджень та технологій в промисловості cryptocurrency exchange rate; forecasting algorithm; social media posts; ranking of a group of experts; information technology of intellectual analysis |
title | Forecasting the cryptocurrency exchange rate based on the ranking of expert opinions |
title_full | Forecasting the cryptocurrency exchange rate based on the ranking of expert opinions |
title_fullStr | Forecasting the cryptocurrency exchange rate based on the ranking of expert opinions |
title_full_unstemmed | Forecasting the cryptocurrency exchange rate based on the ranking of expert opinions |
title_short | Forecasting the cryptocurrency exchange rate based on the ranking of expert opinions |
title_sort | forecasting the cryptocurrency exchange rate based on the ranking of expert opinions |
topic | cryptocurrency exchange rate; forecasting algorithm; social media posts; ranking of a group of experts; information technology of intellectual analysis |
url | https://www.itssi-journal.com/index.php/ittsi/article/view/438 |
work_keys_str_mv | AT olenagavrilenko forecastingthecryptocurrencyexchangeratebasedontherankingofexpertopinions AT mihajlomâgkij forecastingthecryptocurrencyexchangeratebasedontherankingofexpertopinions |