ANALYSIS OF DIGITAL CRYPTOCURRENCY MARKET FORECASTING METHODS AND MODELS

Bohdan Bebeshko
{"title":"ANALYSIS OF DIGITAL CRYPTOCURRENCY MARKET FORECASTING METHODS AND MODELS","authors":"Bohdan Bebeshko","doi":"10.28925/2663-4023.2022.18.163174","DOIUrl":null,"url":null,"abstract":"With the development of financial institutions, this application software and related information technologies are used not only by specialists, but also by ordinary citizens to solve tasks that a few years ago seemed to be within the competence of only mathematicians specializing, for example, in building forecasting models. It can be noted that the collaboration of IT with application software, as well as with the mathematical apparatus most typical for forecasting tasks, gives good results. In particular, this applies to the Central Bank market. The study is devoted to the problem of approaches to the selection of methods and strategies for analysis and forecasting of the central bank markets, which is an urgent issue today. Far from all possible methods and strategies have sufficient coverage in the scientific information space, which prompts the need to analyze and systematize already existing information in this field. Accordingly, basically. the purpose of the study is to analyze and systematize the theoretical foundations of existing approaches to forecasting the CCV market. An analysis and systematization of the theoretical foundations of existing approaches to forecasting the CCV market was carried out. Generalized advantages and disadvantages of structural methods and models used for making market forecasts were outlined. A comparative analysis of ANN models was carried out in terms of their use for market analysis tasks. Among the analyzed ANN models are the following: CNN-2l, CNN-3l, LSTM, sLSTM, BiLSTM, GRU, CLSTM, MLP and RFBNN. The analysis and testing of existing models provided results that provide a wide scope for further research and study.","PeriodicalId":198390,"journal":{"name":"Cybersecurity: Education, Science, Technique","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cybersecurity: Education, Science, Technique","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.28925/2663-4023.2022.18.163174","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

With the development of financial institutions, this application software and related information technologies are used not only by specialists, but also by ordinary citizens to solve tasks that a few years ago seemed to be within the competence of only mathematicians specializing, for example, in building forecasting models. It can be noted that the collaboration of IT with application software, as well as with the mathematical apparatus most typical for forecasting tasks, gives good results. In particular, this applies to the Central Bank market. The study is devoted to the problem of approaches to the selection of methods and strategies for analysis and forecasting of the central bank markets, which is an urgent issue today. Far from all possible methods and strategies have sufficient coverage in the scientific information space, which prompts the need to analyze and systematize already existing information in this field. Accordingly, basically. the purpose of the study is to analyze and systematize the theoretical foundations of existing approaches to forecasting the CCV market. An analysis and systematization of the theoretical foundations of existing approaches to forecasting the CCV market was carried out. Generalized advantages and disadvantages of structural methods and models used for making market forecasts were outlined. A comparative analysis of ANN models was carried out in terms of their use for market analysis tasks. Among the analyzed ANN models are the following: CNN-2l, CNN-3l, LSTM, sLSTM, BiLSTM, GRU, CLSTM, MLP and RFBNN. The analysis and testing of existing models provided results that provide a wide scope for further research and study.
数字加密货币市场预测方法与模型分析
随着金融机构的发展,这种应用软件和相关的信息技术不仅被专家使用,而且也被普通市民用来解决几年前似乎只有数学家才能胜任的任务,例如,建立预测模型。值得注意的是,信息技术与应用软件的合作,以及与预测任务中最典型的数学设备的合作,取得了良好的结果。这尤其适用于央行市场。本研究致力于分析和预测中央银行市场的方法和策略选择的方法问题,这是当今的一个紧迫问题。在科学信息空间中,并非所有可能的方法和策略都有足够的覆盖范围,这促使人们需要对该领域已有的信息进行分析和系统化。因此,基本上。本研究的目的是对现有CCV市场预测方法的理论基础进行分析和系统化。对现有CCV市场预测方法的理论基础进行了分析和梳理。概述了用于市场预测的结构方法和模型的一般优缺点。对人工神经网络模型在市场分析任务中的应用进行了比较分析。所分析的ANN模型包括:cnn - 21、cnn - 31、LSTM、sLSTM、BiLSTM、GRU、CLSTM、MLP和RFBNN。对现有模型的分析和测试提供的结果为进一步的研究和研究提供了广阔的空间。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信