利用变压器神经网络和技术指标加强加密货币的价格预测

Mohammad Ali Labbaf Khaniki, Mohammad Manthouri
{"title":"利用变压器神经网络和技术指标加强加密货币的价格预测","authors":"Mohammad Ali Labbaf Khaniki, Mohammad Manthouri","doi":"arxiv-2403.03606","DOIUrl":null,"url":null,"abstract":"This study presents an innovative approach for predicting cryptocurrency time\nseries, specifically focusing on Bitcoin, Ethereum, and Litecoin. The\nmethodology integrates the use of technical indicators, a Performer neural\nnetwork, and BiLSTM (Bidirectional Long Short-Term Memory) to capture temporal\ndynamics and extract significant features from raw cryptocurrency data. The\napplication of technical indicators, such facilitates the extraction of\nintricate patterns, momentum, volatility, and trends. The Performer neural\nnetwork, employing Fast Attention Via positive Orthogonal Random features\n(FAVOR+), has demonstrated superior computational efficiency and scalability\ncompared to the traditional Multi-head attention mechanism in Transformer\nmodels. Additionally, the integration of BiLSTM in the feedforward network\nenhances the model's capacity to capture temporal dynamics in the data,\nprocessing it in both forward and backward directions. This is particularly\nadvantageous for time series data where past and future data points can\ninfluence the current state. The proposed method has been applied to the hourly\nand daily timeframes of the major cryptocurrencies and its performance has been\nbenchmarked against other methods documented in the literature. The results\nunderscore the potential of the proposed method to outperform existing models,\nmarking a significant progression in the field of cryptocurrency price\nprediction.","PeriodicalId":501294,"journal":{"name":"arXiv - QuantFin - Computational Finance","volume":"9 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhancing Price Prediction in Cryptocurrency Using Transformer Neural Network and Technical Indicators\",\"authors\":\"Mohammad Ali Labbaf Khaniki, Mohammad Manthouri\",\"doi\":\"arxiv-2403.03606\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study presents an innovative approach for predicting cryptocurrency time\\nseries, specifically focusing on Bitcoin, Ethereum, and Litecoin. The\\nmethodology integrates the use of technical indicators, a Performer neural\\nnetwork, and BiLSTM (Bidirectional Long Short-Term Memory) to capture temporal\\ndynamics and extract significant features from raw cryptocurrency data. The\\napplication of technical indicators, such facilitates the extraction of\\nintricate patterns, momentum, volatility, and trends. The Performer neural\\nnetwork, employing Fast Attention Via positive Orthogonal Random features\\n(FAVOR+), has demonstrated superior computational efficiency and scalability\\ncompared to the traditional Multi-head attention mechanism in Transformer\\nmodels. Additionally, the integration of BiLSTM in the feedforward network\\nenhances the model's capacity to capture temporal dynamics in the data,\\nprocessing it in both forward and backward directions. This is particularly\\nadvantageous for time series data where past and future data points can\\ninfluence the current state. The proposed method has been applied to the hourly\\nand daily timeframes of the major cryptocurrencies and its performance has been\\nbenchmarked against other methods documented in the literature. The results\\nunderscore the potential of the proposed method to outperform existing models,\\nmarking a significant progression in the field of cryptocurrency price\\nprediction.\",\"PeriodicalId\":501294,\"journal\":{\"name\":\"arXiv - QuantFin - Computational Finance\",\"volume\":\"9 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - Computational Finance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2403.03606\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - Computational Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2403.03606","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

本研究提出了一种预测加密货币时间序列的创新方法,特别关注比特币、以太坊和莱特币。该方法综合使用技术指标、Performer 神经网络和 BiLSTM(双向长短期记忆)来捕捉时间动态,并从原始加密货币数据中提取重要特征。技术指标的应用有助于提取错综复杂的模式、动量、波动性和趋势。Performer 神经网络采用了 "正交随机特征快速注意力"(FAVOR+),与传统的 Transformermodels 多头注意力机制相比,具有更高的计算效率和可扩展性。此外,将 BiLSTM 集成到前馈网络中还增强了模型捕捉数据中时间动态的能力,并能在前向和后向两个方向上处理数据。这对于时间序列数据尤为有利,因为过去和未来的数据点都会对当前状态产生影响。我们已将所提出的方法应用于主要加密货币的小时和日时间框架,并将其性能与文献中记载的其他方法进行了比较。结果表明,所提出的方法具有超越现有模型的潜力,标志着加密货币价格预测领域取得了重大进展。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Enhancing Price Prediction in Cryptocurrency Using Transformer Neural Network and Technical Indicators
This study presents an innovative approach for predicting cryptocurrency time series, specifically focusing on Bitcoin, Ethereum, and Litecoin. The methodology integrates the use of technical indicators, a Performer neural network, and BiLSTM (Bidirectional Long Short-Term Memory) to capture temporal dynamics and extract significant features from raw cryptocurrency data. The application of technical indicators, such facilitates the extraction of intricate patterns, momentum, volatility, and trends. The Performer neural network, employing Fast Attention Via positive Orthogonal Random features (FAVOR+), has demonstrated superior computational efficiency and scalability compared to the traditional Multi-head attention mechanism in Transformer models. Additionally, the integration of BiLSTM in the feedforward network enhances the model's capacity to capture temporal dynamics in the data, processing it in both forward and backward directions. This is particularly advantageous for time series data where past and future data points can influence the current state. The proposed method has been applied to the hourly and daily timeframes of the major cryptocurrencies and its performance has been benchmarked against other methods documented in the literature. The results underscore the potential of the proposed method to outperform existing models, marking a significant progression in the field of cryptocurrency price prediction.
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
自引率
0.00%
发文量
0
期刊最新文献
A deep primal-dual BSDE method for optimal stopping problems Robust financial calibration: a Bayesian approach for neural SDEs MANA-Net: Mitigating Aggregated Sentiment Homogenization with News Weighting for Enhanced Market Prediction QuantFactor REINFORCE: Mining Steady Formulaic Alpha Factors with Variance-bounded REINFORCE Signature of maturity in cryptocurrency volatility
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1