Sovia, Rini and Yanto, Musli and Budiman, Arif and Mayola, Liga and Saputra, Dio (2019) Backpropagation neural network prediction for cryptocurrency bitcoin prices. Journal of Physics: Conference Series, 1339. 012060. ISSN 1742-6588
|
Text
Backpropagation neural network prediction for.pdf Download (802kB) | Preview |
Abstract
The value of bitcoin currency is very volatile, hard to guess for every hour, so many of the bitcoin traders suffer losses because they are wrong in managing their bitcoin assets. Changes in the price of bitcoin itself are influenced by many things such as the closing of the bitcoin market in a country, the occurrence of hacker attacks on the bitcoin blockchain and the emergence of new coins that use technology similar to bitcoin. But when a stable market situation changes the price of bitcoin is purely influenced by market forces. By mplementing an artificial neural network using backpropagation method, it will be able to predict the price of bitcoin by giving a form of predictive results that are strengthened with a fairly good value of accuracy. This research begins by determining prediction variables with target values that can be determined based on previous bitcoin prices. This artificial neural network process is able to conduct training and testing of data based on network patterns that have been formed, then the results of training and testing of the network will be analysed again, so that at the last stage the best network patterns will be used in the prediction process.
| Item Type: | Article |
|---|---|
| Subjects: | 0 Research > Ilmu Komputer > Jaringan Saraf Tiruan |
| Divisions/ Fakultas/ Prodi: | Fakultas Ilmu Komputer |
| Depositing User: | Administrator |
| Date Deposited: | 15 Sep 2021 05:09 |
| Last Modified: | 15 Sep 2021 05:09 |
| URI: | http://repository.upiyptk.ac.id/id/eprint/3115 |
Actions (login required)
 |
View Item |
