Corrected Triple Correction Method, CNN and Transfer Learning for Prediction the Realized Volatility of Bitcoin and E-Mini S&P500

IF 0.8 Q2 MATHEMATICS
V. A. Manevich
{"title":"Corrected Triple Correction Method, CNN and Transfer Learning for Prediction the Realized Volatility of Bitcoin and E-Mini S&P500","authors":"V. A. Manevich","doi":"10.1134/s1995080224600705","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Compares ARMA models, boosting, neural network models, HAR_RV models and proposes a new method for predicting one day ahead realized volatility of financial series. HAR_RV models are taken as compared classical volatility prediction models. In addition, the phenomenon of transfer learning for boosting and neural network models is investigated. Bitcoin and E-mini S&amp;P500 are chosen as examples. The realized volatility is calculated based on intraday (intraday—24 hours) data. The calculation is based on the closing values of the internal five-minute intervals. Comparisons are made both within and between the two intervals. The intervals considered are January 1, 2018–January 1, 2022 and January 1, 2018–April 2, 2023. Since there were structural changes in the markets during these intervals, the models are estimated in sliding windows of 399 days length. For each time series, we compare three-parameter enumeration boosting, about 10 different neural network architectures, ARMA models, the newly proposed CTCM method, and various training transfer and training sample expansion options. It is shown that ARMA and HAR_RV models are generally inferior to other listed methods and models. The CTCM model and neural networks of CNN architecture are the most suitable for financial time series forecasting and show the best results. Although transfer learning shows no improvement in terms of forecast precision and yields little decline. It requires more extensive and detailed study. The smallest MAPEs for Bitcoin and E-mini S&amp;P500 realized volatility forecasts are achieved by the newly proposed CTCM model and are 21.075%, 25.311% on the first interval and 21.996%, 26.549% on the second interval, respectively.</p>","PeriodicalId":46135,"journal":{"name":"Lobachevskii Journal of Mathematics","volume":"25 1","pages":""},"PeriodicalIF":0.8000,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Lobachevskii Journal of Mathematics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1134/s1995080224600705","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATHEMATICS","Score":null,"Total":0}
引用次数: 0

Abstract

Compares ARMA models, boosting, neural network models, HAR_RV models and proposes a new method for predicting one day ahead realized volatility of financial series. HAR_RV models are taken as compared classical volatility prediction models. In addition, the phenomenon of transfer learning for boosting and neural network models is investigated. Bitcoin and E-mini S&P500 are chosen as examples. The realized volatility is calculated based on intraday (intraday—24 hours) data. The calculation is based on the closing values of the internal five-minute intervals. Comparisons are made both within and between the two intervals. The intervals considered are January 1, 2018–January 1, 2022 and January 1, 2018–April 2, 2023. Since there were structural changes in the markets during these intervals, the models are estimated in sliding windows of 399 days length. For each time series, we compare three-parameter enumeration boosting, about 10 different neural network architectures, ARMA models, the newly proposed CTCM method, and various training transfer and training sample expansion options. It is shown that ARMA and HAR_RV models are generally inferior to other listed methods and models. The CTCM model and neural networks of CNN architecture are the most suitable for financial time series forecasting and show the best results. Although transfer learning shows no improvement in terms of forecast precision and yields little decline. It requires more extensive and detailed study. The smallest MAPEs for Bitcoin and E-mini S&P500 realized volatility forecasts are achieved by the newly proposed CTCM model and are 21.075%, 25.311% on the first interval and 21.996%, 26.549% on the second interval, respectively.

Abstract Image

预测比特币和 E-Mini S&P500 实际波动率的修正三重校正法、CNN 和迁移学习法
摘要比较了 ARMA 模型、boosting 模型、神经网络模型、HAR_RV 模型,并提出了一种预测金融序列提前一天已实现波动率的新方法。HAR_RV 模型是与经典波动率预测模型相比较的。此外,还研究了提升模型和神经网络模型的迁移学习现象。以比特币和 E-mini S&P500 指数为例。已实现波动率根据盘中(盘中 24 小时)数据计算。计算基于内部五分钟间隔的收盘值。在两个区间内和区间之间进行比较。考虑的区间为 2018 年 1 月 1 日至 2022 年 1 月 1 日和 2018 年 1 月 1 日至 2023 年 4 月 2 日。由于在这些区间内市场发生了结构性变化,因此模型以 399 天的滑动窗口进行估计。对于每个时间序列,我们比较了三参数枚举提升、约 10 种不同的神经网络架构、ARMA 模型、新提出的 CTCM 方法以及各种训练转移和训练样本扩展选项。结果表明,ARMA 和 HAR_RV 模型总体上不如其他列出的方法和模型。CTCM 模型和 CNN 架构的神经网络最适合用于金融时间序列预测,并显示出最佳效果。尽管迁移学习在预测精度方面没有任何改进,而且下降幅度很小。这需要更广泛、更详细的研究。新提出的 CTCM 模型对比特币和 E-mini S&P500 已实现波动率预测的 MAPE 最小,在第一个区间分别为 21.075%、25.311%,在第二个区间分别为 21.996%、26.549%。
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
CiteScore
1.50
自引率
42.90%
发文量
127
期刊介绍: Lobachevskii Journal of Mathematics is an international peer reviewed journal published in collaboration with the Russian Academy of Sciences and Kazan Federal University. The journal covers mathematical topics associated with the name of famous Russian mathematician Nikolai Lobachevsky (Lobachevskii). The journal publishes research articles on geometry and topology, algebra, complex analysis, functional analysis, differential equations and mathematical physics, probability theory and stochastic processes, computational mathematics, mathematical modeling, numerical methods and program complexes, computer science, optimal control, and theory of algorithms as well as applied mathematics. The journal welcomes manuscripts from all countries in the English language.
×
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