GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top Cryptocurrencies
Cryptocurrencies are currently traded worldwide, with hundreds of different currencies in existence and even more on the way. This study implements some statistical and machine learning approaches for cryptocurrency investments. First, we implement <i>GJR-GARCH</i> over the <i>GARC...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-09-01
|
Series: | Journal of Risk and Financial Management |
Subjects: | |
Online Access: | https://www.mdpi.com/1911-8074/14/9/421 |
id |
doaj-baee06d16c6844dbb41c7580e2c25038 |
---|---|
record_format |
Article |
spelling |
doaj-baee06d16c6844dbb41c7580e2c250382021-09-26T00:32:32ZengMDPI AGJournal of Risk and Financial Management1911-80661911-80742021-09-011442142110.3390/jrfm14090421GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top CryptocurrenciesFahad Mostafa0Pritam Saha1Mohammad Rafiqul Islam2Nguyet Nguyen3Department of Mathematics and Statistics, Texas Tech University, Lubbock, TX 79409, USARawls College of Business, Texas Tech University, Lubbock, TX 79409, USADepartment of Mathematics, Florida State University, Tallahassee, FL 32306, USADepartment of Mathematics and Statistics, Youngstown State University, Youngstown, OH 44555, USACryptocurrencies are currently traded worldwide, with hundreds of different currencies in existence and even more on the way. This study implements some statistical and machine learning approaches for cryptocurrency investments. First, we implement <i>GJR-GARCH</i> over the <i>GARCH</i> model to estimate the volatility of ten popular cryptocurrencies based on market capitalization: Bitcoin, Bitcoin Cash, Bitcoin SV, Chainlink, EOS, Ethereum, Litecoin, TETHER, Tezos, and XRP. Then, we use Monte Carlo simulations to generate the conditional variance of the cryptocurrencies using the <i>GJR-GARCH</i> model, and calculate the value at risk (VaR) of the simulations. We also estimate the tail-risk using VaR backtesting. Finally, we use an artificial neural network (<i>ANN</i>) for predicting the prices of the ten cryptocurrencies. The graphical analysis and mean square errors (<i>MSEs</i>) from the <i>ANN</i> models confirmed that the predicted prices are close to the market prices. For some cryptocurrencies, the <i>ANN</i> models perform better than traditional <i>ARIMA</i> models.https://www.mdpi.com/1911-8074/14/9/421artificial neural networkcryptocurrency<i>GJR-GARCH</i><i>NIG</i>Monte Carlo simulationvalue at risk backtesting |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fahad Mostafa Pritam Saha Mohammad Rafiqul Islam Nguyet Nguyen |
spellingShingle |
Fahad Mostafa Pritam Saha Mohammad Rafiqul Islam Nguyet Nguyen GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top Cryptocurrencies Journal of Risk and Financial Management artificial neural network cryptocurrency <i>GJR-GARCH</i> <i>NIG</i> Monte Carlo simulation value at risk backtesting |
author_facet |
Fahad Mostafa Pritam Saha Mohammad Rafiqul Islam Nguyet Nguyen |
author_sort |
Fahad Mostafa |
title |
GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top Cryptocurrencies |
title_short |
GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top Cryptocurrencies |
title_full |
GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top Cryptocurrencies |
title_fullStr |
GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top Cryptocurrencies |
title_full_unstemmed |
GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top Cryptocurrencies |
title_sort |
gjr-garch volatility modeling under nig and ann for predicting top cryptocurrencies |
publisher |
MDPI AG |
series |
Journal of Risk and Financial Management |
issn |
1911-8066 1911-8074 |
publishDate |
2021-09-01 |
description |
Cryptocurrencies are currently traded worldwide, with hundreds of different currencies in existence and even more on the way. This study implements some statistical and machine learning approaches for cryptocurrency investments. First, we implement <i>GJR-GARCH</i> over the <i>GARCH</i> model to estimate the volatility of ten popular cryptocurrencies based on market capitalization: Bitcoin, Bitcoin Cash, Bitcoin SV, Chainlink, EOS, Ethereum, Litecoin, TETHER, Tezos, and XRP. Then, we use Monte Carlo simulations to generate the conditional variance of the cryptocurrencies using the <i>GJR-GARCH</i> model, and calculate the value at risk (VaR) of the simulations. We also estimate the tail-risk using VaR backtesting. Finally, we use an artificial neural network (<i>ANN</i>) for predicting the prices of the ten cryptocurrencies. The graphical analysis and mean square errors (<i>MSEs</i>) from the <i>ANN</i> models confirmed that the predicted prices are close to the market prices. For some cryptocurrencies, the <i>ANN</i> models perform better than traditional <i>ARIMA</i> models. |
topic |
artificial neural network cryptocurrency <i>GJR-GARCH</i> <i>NIG</i> Monte Carlo simulation value at risk backtesting |
url |
https://www.mdpi.com/1911-8074/14/9/421 |
work_keys_str_mv |
AT fahadmostafa gjrgarchvolatilitymodelingundernigandannforpredictingtopcryptocurrencies AT pritamsaha gjrgarchvolatilitymodelingundernigandannforpredictingtopcryptocurrencies AT mohammadrafiqulislam gjrgarchvolatilitymodelingundernigandannforpredictingtopcryptocurrencies AT nguyetnguyen gjrgarchvolatilitymodelingundernigandannforpredictingtopcryptocurrencies |
_version_ |
1714248828960374784 |