A Deep Learning based Model for Predicting the future prices of Bitcoin

2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN) Pub Date : 2023-05-05 DOI:10.1109/ViTECoN58111.2023.10157841

Harshith Singathala, Jyotsna Malla, J. Jayashree, J. Vijayashree

{"title":"A Deep Learning based Model for Predicting the future prices of Bitcoin","authors":"Harshith Singathala, Jyotsna Malla, J. Jayashree, J. Vijayashree","doi":"10.1109/ViTECoN58111.2023.10157841","DOIUrl":null,"url":null,"abstract":"Bitcoin was introduced in 2009 and is the earliest cryp- tocurrency in the world. It has gained immense popularity and has attracted a huge consumer base owing to its ever-increasing market capitalization. This has led to many traders and investors being interested in knowing the future prices of these cryptocurrencies to gain profits. Researchers have contributed several works in the field of predicting the future cryptocurrency but with very low accuracy. The aim of this paper is to propose a bitcoin price prediction model which will help predict the future prices of bitcoin. Different deep-learning models are involved in the proposed prediction model namely Gated Recurrent Unit(GRU), Long Short-Term Memory(LSTM), Bidirectional GRU (BiGRU) and Bidirectional LSTM (BiLSTM). The performance analysis of the different models shows that BiGRU is able to predict the future bitcoin prices with the lowest Mean Absolute Error Percentage(MAPE) score of 3.41","PeriodicalId":407488,"journal":{"name":"2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ViTECoN58111.2023.10157841","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Bitcoin was introduced in 2009 and is the earliest cryp- tocurrency in the world. It has gained immense popularity and has attracted a huge consumer base owing to its ever-increasing market capitalization. This has led to many traders and investors being interested in knowing the future prices of these cryptocurrencies to gain profits. Researchers have contributed several works in the field of predicting the future cryptocurrency but with very low accuracy. The aim of this paper is to propose a bitcoin price prediction model which will help predict the future prices of bitcoin. Different deep-learning models are involved in the proposed prediction model namely Gated Recurrent Unit(GRU), Long Short-Term Memory(LSTM), Bidirectional GRU (BiGRU) and Bidirectional LSTM (BiLSTM). The performance analysis of the different models shows that BiGRU is able to predict the future bitcoin prices with the lowest Mean Absolute Error Percentage(MAPE) score of 3.41

查看原文本刊更多论文

预测比特币未来价格的深度学习模型

比特币于2009年推出，是世界上最早的加密货币。由于其不断增长的市值，它已经获得了巨大的人气，并吸引了庞大的消费者基础。这导致许多交易者和投资者有兴趣了解这些加密货币的未来价格以获得利润。研究人员在预测未来加密货币领域贡献了几项工作，但准确性非常低。本文的目的是提出一个比特币价格预测模型，以帮助预测比特币未来的价格。所提出的预测模型涉及不同的深度学习模型，即门控循环单元(GRU)，长短期记忆(LSTM)，双向GRU (BiGRU)和双向LSTM (BiLSTM)。不同模型的性能分析表明，BiGRU能够预测未来比特币价格，平均绝对误差百分比(MAPE)得分最低，为3.41

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

2023 2nd International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies (ViTECoN)

自引率

0.00%

发文量