EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Comparing Volatility and Neural Network Models for Forecasting Bitcoin Prices in Indonesian Rupiah

Raihan Akbar, I Wayan Mangku, Bib Paruhum Silalahi

ZERO: Jurnal Sains, Matematika dan Terapan · 08.08.2026 · 10 (2) · 731

DOI: 10.30829/zero.v10i2.30726 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ZERO: Jurnal Sains, Matematika dan Terapan, online erschienen am 08.08.2026. Verfasst von Raihan Akbar und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As Indonesia emerges among Southeast Asia's largest cryptocurrency markets, forecasting Bitcoin priced in rupiah (BTC/IDR) has gained practical relevance, yet most research focuses on BTC/USD and overlooks domestic macroeconomic conditions. This study tests whether augmenting an Exponential GARCH with Exogenous Variables (eGARCH-X) model with a Nonlinear Autoregressive network with eXogenous inputs (NARX) improves forecasts of weekly BTC/IDR log returns, using IHSG, USD/IDR, gold price, and BI rate as exogenous inputs. Using 437 weekly observations from January 2018 to June 2026, the hybrid was benchmarked against eGARCH-X, NARX, and a restricted eGARCH without exogenous terms across three splits, evaluated with RMSE, MAE, directional accuracy, and the Diebold­­­­ Mariano test, with each network comparison replicated over ten random initializations. The eGARCH identified a well-determined conditional variance process: volatility was highly persistent (0.976), responded asymmetrically to the sign of innovations (0.038, p = 0.010), and displayed heavy tails, with standardized residuals passing all diagnostics. No model differed significantly from the eGARCH-X benchmark, directional accuracy was indistinguishable from chance throughout (43.7–55.5%), and the exogenous regressors were insignificant both inSeaksample and out-of-sample. Weekly BTC/IDR returns thus appear tractable in their variance but close to unforecastable in their conditional mean, locating the practical value of these models in volatility estimation rather than directional prediction.

Zitieren

APA

Akbar, R., Mangku, I. W., & Silalahi, B. P. (2026). Comparing Volatility and Neural Network Models for Forecasting Bitcoin Prices in Indonesian Rupiah. ZERO: Jurnal Sains, Matematika dan Terapan, 10(2), 731. https://doi.org/10.30829/zero.v10i2.30726

Vancouver

Akbar R, Mangku IW, Silalahi BP. Comparing Volatility and Neural Network Models for Forecasting Bitcoin Prices in Indonesian Rupiah. ZERO: Jurnal Sains, Matematika dan Terapan. 2026;10(2):731. doi:10.30829/zero.v10i2.30726

BibTeX
@article{Akbar2026,
  author = {Akbar, Raihan and Mangku, I Wayan and Silalahi, Bib Paruhum},
  title = {Comparing Volatility and Neural Network Models for Forecasting Bitcoin Prices in Indonesian Rupiah},
  journal = {ZERO: Jurnal Sains, Matematika dan Terapan},
  year = {2026},
  volume = {10},
  number = {2},
  pages = {731},
  doi = {10.30829/zero.v10i2.30726}
}
Kostenlos starten →