Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory

Digitization is changing our world, creating innovative finance channels and emerging technology such as cryptocurrencies, which are applications of blockchain technology. However, cryptocurrency price volatility is one of this technology’s main trade-offs. In this paper, we explore a time series an...

Full description

Bibliographic Details
Main Authors: Jacques Phillipe Fleischer, Gregor von Laszewski, Carlos Theran, Yohn Jairo Parra Bautista
Format: Article
Language:English
Published: MDPI AG 2022-07-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/15/7/230
_version_ 1797441356884344832
author Jacques Phillipe Fleischer
Gregor von Laszewski
Carlos Theran
Yohn Jairo Parra Bautista
author_facet Jacques Phillipe Fleischer
Gregor von Laszewski
Carlos Theran
Yohn Jairo Parra Bautista
author_sort Jacques Phillipe Fleischer
collection DOAJ
description Digitization is changing our world, creating innovative finance channels and emerging technology such as cryptocurrencies, which are applications of blockchain technology. However, cryptocurrency price volatility is one of this technology’s main trade-offs. In this paper, we explore a time series analysis using deep learning to study the volatility and to understand this behavior. We apply a long short-term memory model to learn the patterns within cryptocurrency close prices and to predict future prices. The proposed model learns from the close values. The performance of this model is evaluated using the root-mean-squared error and by comparing it to an ARIMA model.
first_indexed 2024-03-09T12:21:51Z
format Article
id doaj.art-7186a28b947f4bbf9744eec7fe94f0d3
institution Directory Open Access Journal
issn 1999-4893
language English
last_indexed 2024-03-09T12:21:51Z
publishDate 2022-07-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj.art-7186a28b947f4bbf9744eec7fe94f0d32023-11-30T22:39:37ZengMDPI AGAlgorithms1999-48932022-07-0115723010.3390/a15070230Time Series Analysis of Cryptocurrency Prices Using Long Short-Term MemoryJacques Phillipe Fleischer0Gregor von Laszewski1Carlos Theran2Yohn Jairo Parra Bautista3Kendall Campus, The Honors College at Miami Dade College, 11011 SW 104th St, Miami, FL 33176, USABiocomplexity Institute, University of Virginia, 994 Research Park Blvd, Charlottesville, VA 22911, USAComputer & Information Systems Department, Florida A&M University, 1333 Wahnish Way 308 A Benjamin Banneker Technical Bldg, Tallahassee, FL 32307, USAComputer & Information Systems Department, Florida A&M University, 1333 Wahnish Way 308 A Benjamin Banneker Technical Bldg, Tallahassee, FL 32307, USADigitization is changing our world, creating innovative finance channels and emerging technology such as cryptocurrencies, which are applications of blockchain technology. However, cryptocurrency price volatility is one of this technology’s main trade-offs. In this paper, we explore a time series analysis using deep learning to study the volatility and to understand this behavior. We apply a long short-term memory model to learn the patterns within cryptocurrency close prices and to predict future prices. The proposed model learns from the close values. The performance of this model is evaluated using the root-mean-squared error and by comparing it to an ARIMA model.https://www.mdpi.com/1999-4893/15/7/230predictioncryptocurrencyLSTM
spellingShingle Jacques Phillipe Fleischer
Gregor von Laszewski
Carlos Theran
Yohn Jairo Parra Bautista
Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory
Algorithms
prediction
cryptocurrency
LSTM
title Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory
title_full Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory
title_fullStr Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory
title_full_unstemmed Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory
title_short Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory
title_sort time series analysis of cryptocurrency prices using long short term memory
topic prediction
cryptocurrency
LSTM
url https://www.mdpi.com/1999-4893/15/7/230
work_keys_str_mv AT jacquesphillipefleischer timeseriesanalysisofcryptocurrencypricesusinglongshorttermmemory
AT gregorvonlaszewski timeseriesanalysisofcryptocurrencypricesusinglongshorttermmemory
AT carlostheran timeseriesanalysisofcryptocurrencypricesusinglongshorttermmemory
AT yohnjairoparrabautista timeseriesanalysisofcryptocurrencypricesusinglongshorttermmemory