Hybrid Models for Predicting Cryptocurrency Price Using Financial and Non-Financial Indicators

Tulika Shrivastava; Basem Suleiman; Muhammad Johan Alibasa

doi:10.1007/978-981-99-8696-5_13

Hybrid Models for Predicting Cryptocurrency Price Using Financial and Non-Financial Indicators

Tulika Shrivastava, Basem Suleiman, Muhammad Johan Alibasa

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

Abstract

Cryptocurrency has become very popular and widely used by major businesses as digital currency for online investments and services. However, the price prediction of such digital currencies as Bitcoin and Ethereum is challenging. It involves financial indicators and nonfinancial indicators, such as historical data and social media data, respectively. In this paper, we propose deep learning and hybrid models that effectively incorporate both types of indicators and introduce the optimal algorithms for long-term price prediction of Bitcoin and Ethereum. We conduct extensive experimental evaluations on real data we extracted from financial dataset comprising Yahoo Finance data, and non-financial data consisting of Google Trends data and approximately 30 million related Bitcoin and Ethereum. Our experimental results show that the hybrid models involving LSTM/1D-CNN with ARIMA/ARIMAX outperformed the individual models for the long-term prediction of cryptocurrency prices.

Original language	English
Title of host publication	Data Science and Machine Learning - 21st Australasian Conference, AusDM 2023, Proceedings
Editors	Diana Benavides-Prado, Yun Sing Koh, Sarah Erfani, Philippe Fournier-Viger, Yee Ling Boo
Place of Publication	Singapore Singapore
Publisher	Springer
Pages	177-191
Number of pages	15
ISBN (Electronic)	9789819986965
ISBN (Print)	9789819986958
DOIs	https://doi.org/10.1007/978-981-99-8696-5_13
Publication status	Published - 2024
Externally published	Yes
Event	Australasian Data Science and Machine Learning Conference 2023 - Auckland, New Zealand Duration: 11 Dec 2023 → 13 Dec 2023 Conference number: 21st https://ausdm23.ausdm.org/index.html (Conference website) https://link.springer.com/book/10.1007/978-981-99-8696-5 (Conference proceedings)

Publication series

Name	Communications in Computer and Information Science
Publisher	Springer
Volume	1943
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	Australasian Data Science and Machine Learning Conference 2023
Abbreviated title	AusDM 2023
Country/Territory	New Zealand
City	Auckland
Period	11/12/23 → 13/12/23
Internet address	https://ausdm23.ausdm.org/index.html (Conference website) https://link.springer.com/book/10.1007/978-981-99-8696-5 (Conference proceedings)

Keywords

Cryptocurrency
Deep Learning
Machine Learning
Predictive Models
Price
Sentiment Analysis

Access to Document

10.1007/978-981-99-8696-5_13

Cite this

Shrivastava, T., Suleiman, B., & Alibasa, M. J. (2024). Hybrid Models for Predicting Cryptocurrency Price Using Financial and Non-Financial Indicators. In D. Benavides-Prado, Y. S. Koh, S. Erfani, P. Fournier-Viger, & Y. L. Boo (Eds.), Data Science and Machine Learning - 21st Australasian Conference, AusDM 2023, Proceedings (pp. 177-191). (Communications in Computer and Information Science; Vol. 1943). Springer. https://doi.org/10.1007/978-981-99-8696-5_13

Shrivastava, Tulika ; Suleiman, Basem ; Alibasa, Muhammad Johan. / Hybrid Models for Predicting Cryptocurrency Price Using Financial and Non-Financial Indicators. Data Science and Machine Learning - 21st Australasian Conference, AusDM 2023, Proceedings. editor / Diana Benavides-Prado ; Yun Sing Koh ; Sarah Erfani ; Philippe Fournier-Viger ; Yee Ling Boo. Singapore Singapore : Springer, 2024. pp. 177-191 (Communications in Computer and Information Science).

@inproceedings{25730d5abea245c9ac05e6c45b406367,

title = "Hybrid Models for Predicting Cryptocurrency Price Using Financial and Non-Financial Indicators",

abstract = "Cryptocurrency has become very popular and widely used by major businesses as digital currency for online investments and services. However, the price prediction of such digital currencies as Bitcoin and Ethereum is challenging. It involves financial indicators and nonfinancial indicators, such as historical data and social media data, respectively. In this paper, we propose deep learning and hybrid models that effectively incorporate both types of indicators and introduce the optimal algorithms for long-term price prediction of Bitcoin and Ethereum. We conduct extensive experimental evaluations on real data we extracted from financial dataset comprising Yahoo Finance data, and non-financial data consisting of Google Trends data and approximately 30 million related Bitcoin and Ethereum. Our experimental results show that the hybrid models involving LSTM/1D-CNN with ARIMA/ARIMAX outperformed the individual models for the long-term prediction of cryptocurrency prices.",

keywords = "Cryptocurrency, Deep Learning, Machine Learning, Predictive Models, Price, Sentiment Analysis",

author = "Tulika Shrivastava and Basem Suleiman and Alibasa, \{Muhammad Johan\}",

note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; Australasian Data Science and Machine Learning Conference 2023, AusDM 2023 ; Conference date: 11-12-2023 Through 13-12-2023",

year = "2024",

doi = "10.1007/978-981-99-8696-5\_13",

language = "English",

isbn = "9789819986958",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "177--191",

editor = "Diana Benavides-Prado and Koh, \{Yun Sing\} and Sarah Erfani and Philippe Fournier-Viger and Boo, \{Yee Ling\}",

booktitle = "Data Science and Machine Learning - 21st Australasian Conference, AusDM 2023, Proceedings",

address = "Switzerland",

url = "https://ausdm23.ausdm.org/index.html, https://link.springer.com/book/10.1007/978-981-99-8696-5",

}

Shrivastava, T, Suleiman, B & Alibasa, MJ 2024, Hybrid Models for Predicting Cryptocurrency Price Using Financial and Non-Financial Indicators. in D Benavides-Prado, YS Koh, S Erfani, P Fournier-Viger & YL Boo (eds), Data Science and Machine Learning - 21st Australasian Conference, AusDM 2023, Proceedings. Communications in Computer and Information Science, vol. 1943, Springer, Singapore Singapore, pp. 177-191, Australasian Data Science and Machine Learning Conference 2023, Auckland, New Zealand, 11/12/23. https://doi.org/10.1007/978-981-99-8696-5_13

Hybrid Models for Predicting Cryptocurrency Price Using Financial and Non-Financial Indicators. / Shrivastava, Tulika; Suleiman, Basem; Alibasa, Muhammad Johan.
Data Science and Machine Learning - 21st Australasian Conference, AusDM 2023, Proceedings. ed. / Diana Benavides-Prado; Yun Sing Koh; Sarah Erfani; Philippe Fournier-Viger; Yee Ling Boo. Singapore Singapore: Springer, 2024. p. 177-191 (Communications in Computer and Information Science; Vol. 1943).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

TY - GEN

T1 - Hybrid Models for Predicting Cryptocurrency Price Using Financial and Non-Financial Indicators

AU - Shrivastava, Tulika

AU - Suleiman, Basem

AU - Alibasa, Muhammad Johan

N1 - Conference code: 21st

PY - 2024

Y1 - 2024

N2 - Cryptocurrency has become very popular and widely used by major businesses as digital currency for online investments and services. However, the price prediction of such digital currencies as Bitcoin and Ethereum is challenging. It involves financial indicators and nonfinancial indicators, such as historical data and social media data, respectively. In this paper, we propose deep learning and hybrid models that effectively incorporate both types of indicators and introduce the optimal algorithms for long-term price prediction of Bitcoin and Ethereum. We conduct extensive experimental evaluations on real data we extracted from financial dataset comprising Yahoo Finance data, and non-financial data consisting of Google Trends data and approximately 30 million related Bitcoin and Ethereum. Our experimental results show that the hybrid models involving LSTM/1D-CNN with ARIMA/ARIMAX outperformed the individual models for the long-term prediction of cryptocurrency prices.

AB - Cryptocurrency has become very popular and widely used by major businesses as digital currency for online investments and services. However, the price prediction of such digital currencies as Bitcoin and Ethereum is challenging. It involves financial indicators and nonfinancial indicators, such as historical data and social media data, respectively. In this paper, we propose deep learning and hybrid models that effectively incorporate both types of indicators and introduce the optimal algorithms for long-term price prediction of Bitcoin and Ethereum. We conduct extensive experimental evaluations on real data we extracted from financial dataset comprising Yahoo Finance data, and non-financial data consisting of Google Trends data and approximately 30 million related Bitcoin and Ethereum. Our experimental results show that the hybrid models involving LSTM/1D-CNN with ARIMA/ARIMAX outperformed the individual models for the long-term prediction of cryptocurrency prices.

KW - Cryptocurrency

KW - Deep Learning

KW - Machine Learning

KW - Predictive Models

KW - Price

KW - Sentiment Analysis

UR - https://www.scopus.com/pages/publications/85180629201

U2 - 10.1007/978-981-99-8696-5_13

DO - 10.1007/978-981-99-8696-5_13

M3 - Conference Paper

AN - SCOPUS:85180629201

SN - 9789819986958

T3 - Communications in Computer and Information Science

SP - 177

EP - 191

BT - Data Science and Machine Learning - 21st Australasian Conference, AusDM 2023, Proceedings

A2 - Benavides-Prado, Diana

A2 - Koh, Yun Sing

A2 - Erfani, Sarah

A2 - Fournier-Viger, Philippe

A2 - Boo, Yee Ling

PB - Springer

CY - Singapore Singapore

T2 - Australasian Data Science and Machine Learning Conference 2023

Y2 - 11 December 2023 through 13 December 2023

ER -

Shrivastava T, Suleiman B, Alibasa MJ. Hybrid Models for Predicting Cryptocurrency Price Using Financial and Non-Financial Indicators. In Benavides-Prado D, Koh YS, Erfani S, Fournier-Viger P, Boo YL, editors, Data Science and Machine Learning - 21st Australasian Conference, AusDM 2023, Proceedings. Singapore Singapore: Springer. 2024. p. 177-191. (Communications in Computer and Information Science). doi: 10.1007/978-981-99-8696-5_13