使用机器学习算法预测比特币回报:投资者情绪的影响

IF 3.8 Q2 BUSINESS
Fatma Ben Hamadou, Taicir Mezghani, Ramzi Zouari, Mouna Boujelbène-Abbes
{"title":"使用机器学习算法预测比特币回报:投资者情绪的影响","authors":"Fatma Ben Hamadou, Taicir Mezghani, Ramzi Zouari, Mouna Boujelbène-Abbes","doi":"10.1108/emjb-03-2023-0086","DOIUrl":null,"url":null,"abstract":"Purpose This study aims to assess the predictive performance of various factors on Bitcoin returns, used for the development of a robust forecasting support decision model using machine learning techniques, before and during the COVID-19 pandemic. More specifically, the authors investigate the impact of the investor's sentiment on forecasting the Bitcoin returns. Design/methodology/approach This method uses feature selection techniques to assess the predictive performance of the different factors on the Bitcoin returns. Subsequently, the authors developed a forecasting model for the Bitcoin returns by evaluating the accuracy of three machine learning models, namely the one-dimensional convolutional neural network (1D-CNN), the bidirectional deep learning long short-term memory (BLSTM) neural networks and the support vector machine model. Findings The findings shed light on the importance of the investor's sentiment in enhancing the accuracy of the return forecasts. Furthermore, the investor's sentiment, the economic policy uncertainty (EPU), gold and the financial stress index (FSI) are the top best determinants before the COVID-19 outbreak. However, there was a significant decrease in the importance of financial uncertainty (FSI and EPU) during the COVID-19 pandemic, proving that investors attach much more importance to the sentimental side than to the traditional uncertainty factors. Regarding the forecasting model accuracy, the authors found that the 1D-CNN model showed the lowest prediction error before and during the COVID-19 and outperformed the other models. Therefore, it represents the best-performing algorithm among its tested counterparts, while the BLSTM is the least accurate model. Practical implications Moreover, this study contributes to a better understanding relevant for investors and policymakers to better forecast the returns based on a forecasting model, which can be used as a decision-making support tool. Therefore, the obtained results can drive the investors to uncover potential determinants, which forecast the Bitcoin returns. It actually gives more weight to the sentiment rather than financial uncertainties factors during the pandemic crisis. Originality/value To the authors’ knowledge, this is the first study to have attempted to construct a novel crypto sentiment measure and use it to develop a Bitcoin forecasting model. In fact, the development of a robust forecasting model, using machine learning techniques, offers a practical value as a decision-making support tool for investment strategies and policy formulation.","PeriodicalId":46475,"journal":{"name":"EuroMed Journal of Business","volume":null,"pages":null},"PeriodicalIF":3.8000,"publicationDate":"2023-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Forecasting Bitcoin returns using machine learning algorithms: impact of investor sentiment\",\"authors\":\"Fatma Ben Hamadou, Taicir Mezghani, Ramzi Zouari, Mouna Boujelbène-Abbes\",\"doi\":\"10.1108/emjb-03-2023-0086\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Purpose This study aims to assess the predictive performance of various factors on Bitcoin returns, used for the development of a robust forecasting support decision model using machine learning techniques, before and during the COVID-19 pandemic. More specifically, the authors investigate the impact of the investor's sentiment on forecasting the Bitcoin returns. Design/methodology/approach This method uses feature selection techniques to assess the predictive performance of the different factors on the Bitcoin returns. Subsequently, the authors developed a forecasting model for the Bitcoin returns by evaluating the accuracy of three machine learning models, namely the one-dimensional convolutional neural network (1D-CNN), the bidirectional deep learning long short-term memory (BLSTM) neural networks and the support vector machine model. Findings The findings shed light on the importance of the investor's sentiment in enhancing the accuracy of the return forecasts. Furthermore, the investor's sentiment, the economic policy uncertainty (EPU), gold and the financial stress index (FSI) are the top best determinants before the COVID-19 outbreak. However, there was a significant decrease in the importance of financial uncertainty (FSI and EPU) during the COVID-19 pandemic, proving that investors attach much more importance to the sentimental side than to the traditional uncertainty factors. Regarding the forecasting model accuracy, the authors found that the 1D-CNN model showed the lowest prediction error before and during the COVID-19 and outperformed the other models. Therefore, it represents the best-performing algorithm among its tested counterparts, while the BLSTM is the least accurate model. Practical implications Moreover, this study contributes to a better understanding relevant for investors and policymakers to better forecast the returns based on a forecasting model, which can be used as a decision-making support tool. Therefore, the obtained results can drive the investors to uncover potential determinants, which forecast the Bitcoin returns. It actually gives more weight to the sentiment rather than financial uncertainties factors during the pandemic crisis. Originality/value To the authors’ knowledge, this is the first study to have attempted to construct a novel crypto sentiment measure and use it to develop a Bitcoin forecasting model. In fact, the development of a robust forecasting model, using machine learning techniques, offers a practical value as a decision-making support tool for investment strategies and policy formulation.\",\"PeriodicalId\":46475,\"journal\":{\"name\":\"EuroMed Journal of Business\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.8000,\"publicationDate\":\"2023-09-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"EuroMed Journal of Business\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1108/emjb-03-2023-0086\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BUSINESS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"EuroMed Journal of Business","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1108/emjb-03-2023-0086","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BUSINESS","Score":null,"Total":0}
引用次数: 0

摘要

本研究旨在评估各种因素对比特币回报的预测性能,用于在COVID-19大流行之前和期间使用机器学习技术开发稳健的预测支持决策模型。更具体地说,作者调查了投资者情绪对预测比特币回报的影响。设计/方法/方法该方法使用特征选择技术来评估不同因素对比特币回报的预测性能。随后,作者通过评估三种机器学习模型的准确性,即一维卷积神经网络(1D-CNN),双向深度学习长短期记忆(BLSTM)神经网络和支持向量机模型,开发了比特币回报的预测模型。研究结果揭示了投资者情绪对提高收益预测准确性的重要性。此外,投资者情绪、经济政策不确定性(EPU)、黄金和金融压力指数(FSI)是新冠疫情爆发前的最佳决定因素。然而,在2019冠状病毒病大流行期间,金融不确定性(FSI和EPU)的重要性显著下降,证明投资者更重视情感方面,而不是传统的不确定性因素。在预测模型精度方面,作者发现1D-CNN模型在COVID-19之前和期间的预测误差最低,优于其他模型。因此,它代表了其测试的同类算法中性能最好的算法,而BLSTM是最不准确的模型。此外,本研究有助于投资者和政策制定者更好地理解基于预测模型的收益预测,并可作为决策支持工具。因此,获得的结果可以驱动投资者发现潜在的决定因素,预测比特币的回报。在大流行危机期间,它实际上更重视情绪,而不是金融不确定性因素。据作者所知,这是第一个试图构建一种新的加密情绪测量方法并将其用于开发比特币预测模型的研究。事实上,利用机器学习技术开发一个强大的预测模型,作为投资策略和政策制定的决策支持工具,具有实用价值。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Forecasting Bitcoin returns using machine learning algorithms: impact of investor sentiment
Purpose This study aims to assess the predictive performance of various factors on Bitcoin returns, used for the development of a robust forecasting support decision model using machine learning techniques, before and during the COVID-19 pandemic. More specifically, the authors investigate the impact of the investor's sentiment on forecasting the Bitcoin returns. Design/methodology/approach This method uses feature selection techniques to assess the predictive performance of the different factors on the Bitcoin returns. Subsequently, the authors developed a forecasting model for the Bitcoin returns by evaluating the accuracy of three machine learning models, namely the one-dimensional convolutional neural network (1D-CNN), the bidirectional deep learning long short-term memory (BLSTM) neural networks and the support vector machine model. Findings The findings shed light on the importance of the investor's sentiment in enhancing the accuracy of the return forecasts. Furthermore, the investor's sentiment, the economic policy uncertainty (EPU), gold and the financial stress index (FSI) are the top best determinants before the COVID-19 outbreak. However, there was a significant decrease in the importance of financial uncertainty (FSI and EPU) during the COVID-19 pandemic, proving that investors attach much more importance to the sentimental side than to the traditional uncertainty factors. Regarding the forecasting model accuracy, the authors found that the 1D-CNN model showed the lowest prediction error before and during the COVID-19 and outperformed the other models. Therefore, it represents the best-performing algorithm among its tested counterparts, while the BLSTM is the least accurate model. Practical implications Moreover, this study contributes to a better understanding relevant for investors and policymakers to better forecast the returns based on a forecasting model, which can be used as a decision-making support tool. Therefore, the obtained results can drive the investors to uncover potential determinants, which forecast the Bitcoin returns. It actually gives more weight to the sentiment rather than financial uncertainties factors during the pandemic crisis. Originality/value To the authors’ knowledge, this is the first study to have attempted to construct a novel crypto sentiment measure and use it to develop a Bitcoin forecasting model. In fact, the development of a robust forecasting model, using machine learning techniques, offers a practical value as a decision-making support tool for investment strategies and policy formulation.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
9.80
自引率
19.20%
发文量
61
期刊介绍: The EuroMed Journal of Business (EMJB) is the premier publication facilitating dialogue among researchers from Europe and the Mediterranean. It plays a vital role in generating and disseminating knowledge about various business environments and trends in this region. By offering an up-to-date overview of emerging business practices in specific countries, EMJB serves as a valuable resource for its readers. As the official journal of the EuroMed Academy of Business, EMJB is committed to reflecting the economic growth seen in the European-Mediterranean region. It aims to be a focused and targeted business journal, highlighting environmental opportunities, threats, and marketplace developments in the area. Through its efforts, EMJB promotes collaboration and open dialogue among diverse research cultures and practices. EMJB serves as a platform for debating and disseminating research findings, new research areas and techniques, conceptual developments, and practical applications across various business segments. It seeks to provide a forum for discussing new ideas in business, including theory, practice, and the issues that arise within the field.
×
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