A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series Model
Cryptocurrencies are highly volatile investment assets and are difficult to predict. In this study, various cryptocurrency data are used as features to predict the log-return price of major cryptocurrencies. The original contribution of this study is the selection of the most influential major featu...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Axioms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1680/11/9/448 |
| _version_ | 1797491209964355584 |
|---|---|
| author | Sang-Ha Sung Jong-Min Kim Byung-Kwon Park Sangjin Kim |
| author_facet | Sang-Ha Sung Jong-Min Kim Byung-Kwon Park Sangjin Kim |
| author_sort | Sang-Ha Sung |
| collection | DOAJ |
| description | Cryptocurrencies are highly volatile investment assets and are difficult to predict. In this study, various cryptocurrency data are used as features to predict the log-return price of major cryptocurrencies. The original contribution of this study is the selection of the most influential major features for each cryptocurrency using the volatility features of cryptocurrency, derived from the autoregressive conditional heteroskedasticity (ARCH) and generalized autoregressive conditional heteroskedasticity (GARCH) models, along with the closing price of the cryptocurrency. In addition, we sought to predict the log-return price of cryptocurrencies by implementing various types of time-series model. Based on the selected major features, the log-return price of cryptocurrency was predicted through the autoregressive integrated moving average (ARIMA) time-series prediction model and the artificial neural network-based time-series prediction model. As a result of log-return price prediction, the neural-network-based time-series prediction models showed superior predictive power compared to the traditional time-series prediction model. |
| first_indexed | 2024-03-10T00:44:11Z |
| format | Article |
| id | doaj.art-7b5a8b892f10465f8ee3da1596e2aec6 |
| institution | Directory Open Access Journal |
| issn | 2075-1680 |
| language | English |
| last_indexed | 2024-03-10T00:44:11Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Axioms |
| spelling | doaj.art-7b5a8b892f10465f8ee3da1596e2aec62023-11-23T15:02:12ZengMDPI AGAxioms2075-16802022-09-0111944810.3390/axioms11090448A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series ModelSang-Ha Sung0Jong-Min Kim1Byung-Kwon Park2Sangjin Kim3Department of Management Information Systems, Dong-A University, Busan 49236, KoreaDivision of Science and Mathematics, University of Minnesota-Morris, Morris, MN 56267, USADepartment of Management Information Systems, Dong-A University, Busan 49236, KoreaDepartment of Management Information Systems, Dong-A University, Busan 49236, KoreaCryptocurrencies are highly volatile investment assets and are difficult to predict. In this study, various cryptocurrency data are used as features to predict the log-return price of major cryptocurrencies. The original contribution of this study is the selection of the most influential major features for each cryptocurrency using the volatility features of cryptocurrency, derived from the autoregressive conditional heteroskedasticity (ARCH) and generalized autoregressive conditional heteroskedasticity (GARCH) models, along with the closing price of the cryptocurrency. In addition, we sought to predict the log-return price of cryptocurrencies by implementing various types of time-series model. Based on the selected major features, the log-return price of cryptocurrency was predicted through the autoregressive integrated moving average (ARIMA) time-series prediction model and the artificial neural network-based time-series prediction model. As a result of log-return price prediction, the neural-network-based time-series prediction models showed superior predictive power compared to the traditional time-series prediction model.https://www.mdpi.com/2075-1680/11/9/448time-seriesdeep learningforecastingcryptocurrency |
| spellingShingle | Sang-Ha Sung Jong-Min Kim Byung-Kwon Park Sangjin Kim A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series Model Axioms time-series deep learning forecasting cryptocurrency |
| title | A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series Model |
| title_full | A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series Model |
| title_fullStr | A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series Model |
| title_full_unstemmed | A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series Model |
| title_short | A Study on Cryptocurrency Log-Return Price Prediction Using Multivariate Time-Series Model |
| title_sort | study on cryptocurrency log return price prediction using multivariate time series model |
| topic | time-series deep learning forecasting cryptocurrency |
| url | https://www.mdpi.com/2075-1680/11/9/448 |
| work_keys_str_mv | AT sanghasung astudyoncryptocurrencylogreturnpricepredictionusingmultivariatetimeseriesmodel AT jongminkim astudyoncryptocurrencylogreturnpricepredictionusingmultivariatetimeseriesmodel AT byungkwonpark astudyoncryptocurrencylogreturnpricepredictionusingmultivariatetimeseriesmodel AT sangjinkim astudyoncryptocurrencylogreturnpricepredictionusingmultivariatetimeseriesmodel AT sanghasung studyoncryptocurrencylogreturnpricepredictionusingmultivariatetimeseriesmodel AT jongminkim studyoncryptocurrencylogreturnpricepredictionusingmultivariatetimeseriesmodel AT byungkwonpark studyoncryptocurrencylogreturnpricepredictionusingmultivariatetimeseriesmodel AT sangjinkim studyoncryptocurrencylogreturnpricepredictionusingmultivariatetimeseriesmodel |