Closing Price Prediction of Cryptocurrencies BTC, LTC, and ETH Using a Hybrid ARIMA-LSTM Algorithm

This study aims to develop a hybrid algorithm using the ARIMA model and LSTM-type recurrent neural networks to predict the closing prices of the cryptocurrencies BTC, LTC, and ETH. The methodology includes an exploratory data analysis, followed by the design, implementation, and evaluation of each i...

Full description

Saved in:
Bibliographic Details
Main Authors: Jherson S. Ruiz-Lopez, Miguel Jiménez-Carrión
Format: Article
Language:English
Published: Ital Publication 2025-06-01
Series:HighTech and Innovation Journal
Subjects:
Online Access:https://hightechjournal.org/index.php/HIJ/article/view/1170
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849686034802016256
author Jherson S. Ruiz-Lopez
Miguel Jiménez-Carrión
author_facet Jherson S. Ruiz-Lopez
Miguel Jiménez-Carrión
author_sort Jherson S. Ruiz-Lopez
collection DOAJ
description This study aims to develop a hybrid algorithm using the ARIMA model and LSTM-type recurrent neural networks to predict the closing prices of the cryptocurrencies BTC, LTC, and ETH. The methodology includes an exploratory data analysis, followed by the design, implementation, and evaluation of each individual algorithm as well as the combined hybrid algorithm. The results, after experimentation and evaluation of metrics on the test set, indicated that the ARIMA model was inefficient in predicting the closing prices of cryptocurrencies. On the other hand, the hybrid model for BTC showed significant statistical differences in the metrics, with MAE = $726.21 and MAPE = 1.75%, compared to the LSTM model, which achieved MAE = $729.35 and MAPE = 1.76%. These results indicate better performance from the hybrid model. Regarding the RMSE metric, the hybrid model scored 1157.47, while LSTM scored 1159.99; although statistically equivalent, the hybrid model was numerically better. For the remaining metrics and other cryptocurrencies, both methods were statistically equivalent. For five-day-ahead predictions, the hybrid algorithm continued to yield better results for LTC and ETH.
format Article
id doaj-art-b0f98e431a93400bbbec3d0d4e22b67b
institution DOAJ
issn 2723-9535
language English
publishDate 2025-06-01
publisher Ital Publication
record_format Article
series HighTech and Innovation Journal
spelling doaj-art-b0f98e431a93400bbbec3d0d4e22b67b2025-08-20T03:22:52ZengItal PublicationHighTech and Innovation Journal2723-95352025-06-016210.28991/HIJ-2025-06-02-09Closing Price Prediction of Cryptocurrencies BTC, LTC, and ETH Using a Hybrid ARIMA-LSTM AlgorithmJherson S. Ruiz-Lopez0https://orcid.org/0009-0007-6961-6136Miguel Jiménez-Carrión1https://orcid.org/0000-0001-9632-5085Faculty of Industrial Engineering, Universidad Nacional de Piura, Castilla-Piura, 20002Faculty of Industrial Engineering, Universidad Nacional de Piura, Castilla-Piura, 20002This study aims to develop a hybrid algorithm using the ARIMA model and LSTM-type recurrent neural networks to predict the closing prices of the cryptocurrencies BTC, LTC, and ETH. The methodology includes an exploratory data analysis, followed by the design, implementation, and evaluation of each individual algorithm as well as the combined hybrid algorithm. The results, after experimentation and evaluation of metrics on the test set, indicated that the ARIMA model was inefficient in predicting the closing prices of cryptocurrencies. On the other hand, the hybrid model for BTC showed significant statistical differences in the metrics, with MAE = $726.21 and MAPE = 1.75%, compared to the LSTM model, which achieved MAE = $729.35 and MAPE = 1.76%. These results indicate better performance from the hybrid model. Regarding the RMSE metric, the hybrid model scored 1157.47, while LSTM scored 1159.99; although statistically equivalent, the hybrid model was numerically better. For the remaining metrics and other cryptocurrencies, both methods were statistically equivalent. For five-day-ahead predictions, the hybrid algorithm continued to yield better results for LTC and ETH. https://hightechjournal.org/index.php/HIJ/article/view/1170LSTM NetworksARIMA ModelHybrid ApproachPredictionCryptocurrencies
spellingShingle Jherson S. Ruiz-Lopez
Miguel Jiménez-Carrión
Closing Price Prediction of Cryptocurrencies BTC, LTC, and ETH Using a Hybrid ARIMA-LSTM Algorithm
HighTech and Innovation Journal
LSTM Networks
ARIMA Model
Hybrid Approach
Prediction
Cryptocurrencies
title Closing Price Prediction of Cryptocurrencies BTC, LTC, and ETH Using a Hybrid ARIMA-LSTM Algorithm
title_full Closing Price Prediction of Cryptocurrencies BTC, LTC, and ETH Using a Hybrid ARIMA-LSTM Algorithm
title_fullStr Closing Price Prediction of Cryptocurrencies BTC, LTC, and ETH Using a Hybrid ARIMA-LSTM Algorithm
title_full_unstemmed Closing Price Prediction of Cryptocurrencies BTC, LTC, and ETH Using a Hybrid ARIMA-LSTM Algorithm
title_short Closing Price Prediction of Cryptocurrencies BTC, LTC, and ETH Using a Hybrid ARIMA-LSTM Algorithm
title_sort closing price prediction of cryptocurrencies btc ltc and eth using a hybrid arima lstm algorithm
topic LSTM Networks
ARIMA Model
Hybrid Approach
Prediction
Cryptocurrencies
url https://hightechjournal.org/index.php/HIJ/article/view/1170
work_keys_str_mv AT jhersonsruizlopez closingpricepredictionofcryptocurrenciesbtcltcandethusingahybridarimalstmalgorithm
AT migueljimenezcarrion closingpricepredictionofcryptocurrenciesbtcltcandethusingahybridarimalstmalgorithm