Comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting
In this era of globalization, cryptocurrency is being created as one of the modern investment instruments and an alternative payment method. Many cryptocurrency has been created since the last decade, for examples Bitcoin, Litecoin, Peercoin, Auroracoin, Dogecoin and Ripple. The investment and usage...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2018
|
| Online Access: | http://journalarticle.ukm.my/12742/ http://journalarticle.ukm.my/12742/ http://journalarticle.ukm.my/12742/1/jqma-14-2-paper5.pdf |
| id |
ukm-12742 |
|---|---|
| recordtype |
eprints |
| spelling |
ukm-127422019-04-03T11:08:09Z http://journalarticle.ukm.my/12742/ Comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting Chan Chian Tun, Noriza Majid, In this era of globalization, cryptocurrency is being created as one of the modern investment instruments and an alternative payment method. Many cryptocurrency has been created since the last decade, for examples Bitcoin, Litecoin, Peercoin, Auroracoin, Dogecoin and Ripple. The investment and usage of cryptocurrency is getting popular among the investors and consumers. Bitcoin is one of the most popular cryptocurrencies due to the low-cost-guaranteed transactions and its skyrocketed price. However, the price of Bitcoin depends on the consumers' and investors' speculation. The price volatility has caused losses to many investors. Two forecasting models, which are artificial neural network and the autoregressive integrated moving average (ARIMA) model will be used to forecast the price of Bitcoin. Comparison between the two models will be made and the most accurate model will be selected. Bitcoin price data dated from 1 January 2012 to 28 February 2018 is being used to build the forecasting models. The models will be used to forecast the price of Bitcoin in March 2018, and the predicted values will be used to compare with the actual values. Model building methods, pros and cons of the two models in forecasting will be discussed. Long-term and short-term forecasting will be carried out by using the two models. The suitability of each model in long-term and short-term forecasting will be discussed. Penerbit Universiti Kebangsaan Malaysia 2018-12 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/12742/1/jqma-14-2-paper5.pdf Chan Chian Tun, and Noriza Majid, (2018) Comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting. Journal of Quality Measurement and Analysis, 14 (2). pp. 45-53. ISSN 1823-5670 http://www.ukm.my/jqma/current.html |
| repository_type |
Digital Repository |
| institution_category |
Local University |
| institution |
Universiti Kebangasaan Malaysia |
| building |
UKM Institutional Repository |
| collection |
Online Access |
| language |
English |
| description |
In this era of globalization, cryptocurrency is being created as one of the modern investment instruments and an alternative payment method. Many cryptocurrency has been created since the last decade, for examples Bitcoin, Litecoin, Peercoin, Auroracoin, Dogecoin and Ripple. The investment and usage of cryptocurrency is getting popular among the investors and consumers. Bitcoin is one of the most popular cryptocurrencies due to the low-cost-guaranteed transactions and its skyrocketed price. However, the price of Bitcoin depends on the consumers' and investors' speculation. The price volatility has caused losses to many investors. Two forecasting models, which are artificial neural network and the autoregressive integrated moving average (ARIMA) model will be used to forecast the price of Bitcoin. Comparison between the two models will be made and the most accurate model will be selected. Bitcoin price data dated from 1 January 2012 to 28 February 2018 is being used to build the forecasting models. The models will be used to forecast the price of Bitcoin in March 2018, and the predicted values will be used to compare with the actual values. Model building methods, pros and cons of the two models in forecasting will be discussed. Long-term and short-term forecasting will be carried out by using the two models. The suitability of each model in long-term and short-term forecasting will be discussed. |
| format |
Article |
| author |
Chan Chian Tun, Noriza Majid, |
| spellingShingle |
Chan Chian Tun, Noriza Majid, Comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting |
| author_facet |
Chan Chian Tun, Noriza Majid, |
| author_sort |
Chan Chian Tun, |
| title |
Comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting |
| title_short |
Comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting |
| title_full |
Comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting |
| title_fullStr |
Comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting |
| title_full_unstemmed |
Comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting |
| title_sort |
comparison between artificial neural network and autoregressive integrated moving average model in bitcoin price forecasting |
| publisher |
Penerbit Universiti Kebangsaan Malaysia |
| publishDate |
2018 |
| url |
http://journalarticle.ukm.my/12742/ http://journalarticle.ukm.my/12742/ http://journalarticle.ukm.my/12742/1/jqma-14-2-paper5.pdf |
| first_indexed |
2023-09-18T20:03:17Z |
| last_indexed |
2023-09-18T20:03:17Z |
| _version_ |
1777406991398862848 |