CRYPTOCURRENCY PRICE PREDICTION: A HYBRID LONG SHORT-TERM MEMORY MODEL WITH GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY

Cryptocurrency is a virtual payment instrument currently popular as an investment alternative. One type of cryptocurrency widely used as an investment is Bitcoin due to its high-profit potential and risk due to unstable exchange rate fluctuations. This high exchange rate fluctuation makes trading tr...

Full description

Saved in:
Bibliographic Details
Main Authors: Indah Manfaati Nur, Rifqi Nugrahanto, Fatkhurokhman Fauzi
Format: Article
Language:English
Published: Universitas Pattimura 2023-09-01
Series:Barekeng
Subjects:
Online Access:https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/8566
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849405681115856896
author Indah Manfaati Nur
Rifqi Nugrahanto
Fatkhurokhman Fauzi
author_facet Indah Manfaati Nur
Rifqi Nugrahanto
Fatkhurokhman Fauzi
author_sort Indah Manfaati Nur
collection DOAJ
description Cryptocurrency is a virtual payment instrument currently popular as an investment alternative. One type of cryptocurrency widely used as an investment is Bitcoin due to its high-profit potential and risk due to unstable exchange rate fluctuations. This high exchange rate fluctuation makes trading transactions in the crypto market speculative and highly volatile. To overcome this volatility factor, this research used the Generalized Autoregressive Conditional Heteroscedasticity forecasting method to describe the heteroscedasticity factor, as well as a Recurrent Neural Network (RNN) with long-short-term memory that has feedback in modeling sequential data for time series analysis. The two methods are combined to overcome the dependency of time series data in the long term and the heteroscedastic effect of the volatility of price changes. The results of the GARCH-LSTM hybrid model in this study show a Mean Absolute Percentage Error (MAPE) value of 15.69%. The accuracy value is obtained from the division of training data by 80% and testing data by 20%, with the number of neurons as many as three and epochs of 100 using the Adam optimizer. The MAPE accuracy results show a good prediction in predicting the value.
format Article
id doaj-art-2acedd446b9c47ef8f265db96fb957db
institution Kabale University
issn 1978-7227
2615-3017
language English
publishDate 2023-09-01
publisher Universitas Pattimura
record_format Article
series Barekeng
spelling doaj-art-2acedd446b9c47ef8f265db96fb957db2025-08-20T03:36:37ZengUniversitas PattimuraBarekeng1978-72272615-30172023-09-011731575158410.30598/barekengvol17iss3pp1575-15848566CRYPTOCURRENCY PRICE PREDICTION: A HYBRID LONG SHORT-TERM MEMORY MODEL WITH GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITYIndah Manfaati Nur0Rifqi Nugrahanto1Fatkhurokhman Fauzi2Department of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Muhammadiyah Semarang, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Muhammadiyah Semarang, IndonesiaDepartment of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Muhammadiyah Semarang, IndonesiaCryptocurrency is a virtual payment instrument currently popular as an investment alternative. One type of cryptocurrency widely used as an investment is Bitcoin due to its high-profit potential and risk due to unstable exchange rate fluctuations. This high exchange rate fluctuation makes trading transactions in the crypto market speculative and highly volatile. To overcome this volatility factor, this research used the Generalized Autoregressive Conditional Heteroscedasticity forecasting method to describe the heteroscedasticity factor, as well as a Recurrent Neural Network (RNN) with long-short-term memory that has feedback in modeling sequential data for time series analysis. The two methods are combined to overcome the dependency of time series data in the long term and the heteroscedastic effect of the volatility of price changes. The results of the GARCH-LSTM hybrid model in this study show a Mean Absolute Percentage Error (MAPE) value of 15.69%. The accuracy value is obtained from the division of training data by 80% and testing data by 20%, with the number of neurons as many as three and epochs of 100 using the Adam optimizer. The MAPE accuracy results show a good prediction in predicting the value.https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/8566cryptocurrencygeneralized autoregressive heterocedasticitylong-short tterm memorymapeinvestment
spellingShingle Indah Manfaati Nur
Rifqi Nugrahanto
Fatkhurokhman Fauzi
CRYPTOCURRENCY PRICE PREDICTION: A HYBRID LONG SHORT-TERM MEMORY MODEL WITH GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY
Barekeng
cryptocurrency
generalized autoregressive heterocedasticity
long-short tterm memory
mape
investment
title CRYPTOCURRENCY PRICE PREDICTION: A HYBRID LONG SHORT-TERM MEMORY MODEL WITH GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY
title_full CRYPTOCURRENCY PRICE PREDICTION: A HYBRID LONG SHORT-TERM MEMORY MODEL WITH GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY
title_fullStr CRYPTOCURRENCY PRICE PREDICTION: A HYBRID LONG SHORT-TERM MEMORY MODEL WITH GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY
title_full_unstemmed CRYPTOCURRENCY PRICE PREDICTION: A HYBRID LONG SHORT-TERM MEMORY MODEL WITH GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY
title_short CRYPTOCURRENCY PRICE PREDICTION: A HYBRID LONG SHORT-TERM MEMORY MODEL WITH GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSCEDASTICITY
title_sort cryptocurrency price prediction a hybrid long short term memory model with generalized autoregressive conditional heteroscedasticity
topic cryptocurrency
generalized autoregressive heterocedasticity
long-short tterm memory
mape
investment
url https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/8566
work_keys_str_mv AT indahmanfaatinur cryptocurrencypricepredictionahybridlongshorttermmemorymodelwithgeneralizedautoregressiveconditionalheteroscedasticity
AT rifqinugrahanto cryptocurrencypricepredictionahybridlongshorttermmemorymodelwithgeneralizedautoregressiveconditionalheteroscedasticity
AT fatkhurokhmanfauzi cryptocurrencypricepredictionahybridlongshorttermmemorymodelwithgeneralizedautoregressiveconditionalheteroscedasticity