Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Krisnadana
I Putu Bramasta Priadinata
Faculty of Technology and Informatics, Informatics Study Program, Institut Bisnis dan Teknologi Indonesia, Denpasar, Bali, Indonesia
Computer Science & IT Control & Systems Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Comparative Time Series Forecasting of Major Cryptocurrencies Using the GRU Deep Neural Network I Putu Bramasta Priadinata; I Gede Iwan Sudipa; Sani Inusa Milala
Jurnal Krisnadana Vol 5 No 1 (2025): Jurnal Krisnadana- in Progress September-October 2025
Publisher : Yayasan Sinergi Widya Nusantara (Sidyanusa)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58982/krisnadana.v5i1.977

Abstract

Cryptocurrency investments are increasingly popular due to their potential as digital assets, but high price volatility remains a major challenge in making investment decisions. This study implements the Gated Recurrent Unit (GRU) model to forecast the closing prices of five popular cryptocurrencies: Bitcoin (BTC), Ethereum (ETH), Ripple (XRP), Binance Coin (BNB), and Dogecoin (DOGE), using historical datasets from Yahoo Finance covering the period from November 30, 2019, to November 29, 2024. Performance evaluation was conducted using Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). The results show that the GRU model achieved the best performance for BNB with a MAPE of 2.38% and an RMSE of 17.03, followed by ETH and XRP with MAPE values of 2.51% and 2.64%, respectively. BTC recorded the highest RMSE of 2280.73, reflecting its significant price volatility, while DOGE exhibited the lowest RMSE of 0.01 despite having the highest MAPE of 4.11%. Forecasts for the next six periods indicate that BTC and ETH are likely to experience gradual price increases, XRP and BNB show a flattening trend, and DOGE remains stable with low volatility. This study concludes that the GRU model is effective in forecasting cryptocurrency prices; however, it is recommended to complement the results with fundamental and technical analysis to improve accuracy and support more optimal investment decision-making.
Co-Authors I Gede Iwan Sudipa Sani Inusa Milala