Predicting the Price of Bitcoin Using Hybrid ARIMA and Deep Learning
Recently, Bitcoin as the most popular cryptocurrency, has attracted the attention of many investors and economic actors. The cryptocurrency market has experienced a sharp fluctuation, and one of the challenges is to predict future prices. Undoubtedly, creating methods to predict the price of bitcoin...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Allameh Tabataba'i University Press
2021-06-01
|
| Series: | Muṭāli̒āt-i Mudīriyyat-i Ṣan̒atī |
| Subjects: | |
| Online Access: | https://jims.atu.ac.ir/article_12889_1f536e33db6d8b8d59aa28838fc7378b.pdf |
| _version_ | 1827391865566003200 |
|---|---|
| author | aboosaleh mohammadsharifi Kaveh Kahlili-Damghani farshid abdi soheila sardar |
| author_facet | aboosaleh mohammadsharifi Kaveh Kahlili-Damghani farshid abdi soheila sardar |
| author_sort | aboosaleh mohammadsharifi |
| collection | DOAJ |
| description | Recently, Bitcoin as the most popular cryptocurrency, has attracted the attention of many investors and economic actors. The cryptocurrency market has experienced a sharp fluctuation, and one of the challenges is to predict future prices. Undoubtedly, creating methods to predict the price of bitcoin is very exciting and has a huge impact on determining the profit and loss from its trading in the future. In this study, in order to predict the price of Bitcoin, a combination of the ARIMA model and three types of deep neural networks including RNN, LSTM, and GRU have been used. The main purpose of this study is to determine the effect of deep learning models on the performance of predicting the future price of Bitcoin. In the proposed model, first, the linear components in the data set are separated using ARIMA and the resulting residues are transferred separately to each of the neural networks. The results show that the ARIMA-GRU model has better results for RMSE and MAPE criteria than other models. Combined models also perform better than the traditional ARIMA model in forecasting. |
| first_indexed | 2024-03-08T17:20:33Z |
| format | Article |
| id | doaj.art-28e7570abeb642e387ca4a368ae47409 |
| institution | Directory Open Access Journal |
| issn | 2251-8029 2476-602X |
| language | fas |
| last_indexed | 2024-03-08T17:20:33Z |
| publishDate | 2021-06-01 |
| publisher | Allameh Tabataba'i University Press |
| record_format | Article |
| series | Muṭāli̒āt-i Mudīriyyat-i Ṣan̒atī |
| spelling | doaj.art-28e7570abeb642e387ca4a368ae474092024-01-03T04:46:10ZfasAllameh Tabataba'i University PressMuṭāli̒āt-i Mudīriyyat-i Ṣan̒atī2251-80292476-602X2021-06-01196112514610.22054/jims.2021.52374.248812889Predicting the Price of Bitcoin Using Hybrid ARIMA and Deep Learningaboosaleh mohammadsharifi0Kaveh Kahlili-Damghani1farshid abdi2soheila sardar3Ph.D. Candidate, Information technology management Department, Tehran North Branch, Islamic Azad University, Tehran, Iran.Associate Professor, Industrial Engineering Department, South Tehran Branch, Islamic Azad University, Tehran, Iran.Assistant Professor, Industrial Engineering Department, South Tehran Branch, Islamic Azad University, Tehran, Iran.Assistant Professor, Industrial Management Department, Tehran North Branch, Islamic Azad University, Tehran, Iran.Recently, Bitcoin as the most popular cryptocurrency, has attracted the attention of many investors and economic actors. The cryptocurrency market has experienced a sharp fluctuation, and one of the challenges is to predict future prices. Undoubtedly, creating methods to predict the price of bitcoin is very exciting and has a huge impact on determining the profit and loss from its trading in the future. In this study, in order to predict the price of Bitcoin, a combination of the ARIMA model and three types of deep neural networks including RNN, LSTM, and GRU have been used. The main purpose of this study is to determine the effect of deep learning models on the performance of predicting the future price of Bitcoin. In the proposed model, first, the linear components in the data set are separated using ARIMA and the resulting residues are transferred separately to each of the neural networks. The results show that the ARIMA-GRU model has better results for RMSE and MAPE criteria than other models. Combined models also perform better than the traditional ARIMA model in forecasting.https://jims.atu.ac.ir/article_12889_1f536e33db6d8b8d59aa28838fc7378b.pdfprice predictioncryptocurrencybitcoindeep learningarima |
| spellingShingle | aboosaleh mohammadsharifi Kaveh Kahlili-Damghani farshid abdi soheila sardar Predicting the Price of Bitcoin Using Hybrid ARIMA and Deep Learning Muṭāli̒āt-i Mudīriyyat-i Ṣan̒atī price prediction cryptocurrency bitcoin deep learning arima |
| title | Predicting the Price of Bitcoin Using Hybrid ARIMA and Deep Learning |
| title_full | Predicting the Price of Bitcoin Using Hybrid ARIMA and Deep Learning |
| title_fullStr | Predicting the Price of Bitcoin Using Hybrid ARIMA and Deep Learning |
| title_full_unstemmed | Predicting the Price of Bitcoin Using Hybrid ARIMA and Deep Learning |
| title_short | Predicting the Price of Bitcoin Using Hybrid ARIMA and Deep Learning |
| title_sort | predicting the price of bitcoin using hybrid arima and deep learning |
| topic | price prediction cryptocurrency bitcoin deep learning arima |
| url | https://jims.atu.ac.ir/article_12889_1f536e33db6d8b8d59aa28838fc7378b.pdf |
| work_keys_str_mv | AT aboosalehmohammadsharifi predictingthepriceofbitcoinusinghybridarimaanddeeplearning AT kavehkahlilidamghani predictingthepriceofbitcoinusinghybridarimaanddeeplearning AT farshidabdi predictingthepriceofbitcoinusinghybridarimaanddeeplearning AT soheilasardar predictingthepriceofbitcoinusinghybridarimaanddeeplearning |