Cryptocurrency Price Movement Prediction Using the Hybrid SARIMAX-LSTM Method

Galih Ridha Achmadi*, Ahmad Saikhu, Bilqis Amaliah

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In the digital age, the growth of blockchain technology, underpinning cryptocurrency, has been undeniable since its debut with Bitcoin in 2009. While the cryptocurrency market offers vast profit potential, its price volatility poses a significant challenge to investors and traders. Addressing this challenge, this study proposes a prediction method that fuses SARIMAX and LSTM into a Hybrid SARIMAX-LSTM model, considering trading volume as an exogenous factor. Through evaluation metrics like MSE, RMSE, MAPE, and MAE, it was found that this hybrid model provides more accurate forecasts than singular models, showcasing its potential to counteract cryptocurrency market volatility..

Original languageEnglish
Title of host publication2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages711-716
Number of pages6
ISBN (Electronic)9798350309225
DOIs
Publication statusPublished - 2023
Event2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023 - Lombok, Indonesia
Duration: 14 Nov 202315 Nov 2023

Publication series

Name2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023 - Proceedings

Conference

Conference2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023
Country/TerritoryIndonesia
CityLombok
Period14/11/2315/11/23

Keywords

  • ARIMA
  • SARIMAX
  • bitcoin
  • cryptocurrency
  • neural network
  • prediction
  • time series data

Fingerprint

Dive into the research topics of 'Cryptocurrency Price Movement Prediction Using the Hybrid SARIMAX-LSTM Method'. Together they form a unique fingerprint.

Cite this