Digital Gold Price Prediction on Indogold Platform Using Generalized Autoregressive Conditional Heteroskedasticity Model

Abstract

The digital gold market in Indonesia has experienced significant growth, with transaction values reaching IDR 53.3 trillion during January–November 2024, representing a 556 percent increase compared to the previous year. Despite this rapid growth, digital gold prices exhibit high volatility characterized by volatility clustering and conditional heteroskedasticity that conventional time series models cannot adequately capture. Although the GARCH model has been widely applied to predict physical gold prices, no prior study has specifically examined digital gold price volatility on Indonesian fintech-based trading platforms. This study aims to construct a univariate Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model based solely on historical price movements to predict digital gold prices on the Indogold platform and evaluate its predictive accuracy. Accordingly, the proposed model relies exclusively on historical price data and does not incorporate external macroeconomic variables, such as exchange rates, inflation, interest rates, or international gold prices. The data used consisted of weekly closing prices of digital gold on the Indogold platform from January 5, 2020, to December 29, 2024, totaling 261 observations. Analysis was conducted using RStudio software through logarithmic return calculation, data splitting via trial and error (selected proportion 80%:20%), Augmented Dickey-Fuller stationarity testing, ARMA order identification through ACF and PACF plots followed by AIC-based model selection, ARCH-LM effect testing, GARCH model estimation, and Ljung-Box and ARCH-LM diagnostic testing. The best model identified was ARMA(2,2)-GARCH(1,1) with the conditional variance equation σₜ² = 0.000073 + 0.405334εₜ₋₁² + 0.476482σₜ₋₁². The model passed all diagnostic tests with Ljung-Box p-value = 0.3362 and ARCH-LM p-value = 0.9999. Prediction accuracy evaluation on the test data yielded MAPE = 1.8141%, which is categorized as highly accurate according to Lewis (1982), indicating strong price forecasting performance; however, its suitability as an investment decision-making tool requires further evaluation of return, risk, and trading strategy performance beyond price accuracy alone.