<![CDATA[Illiteracy remains an important educational issue in Indonesia despite various government literacy programs. However, limited studies have compared time series forecasting methods for predicting illiteracy rates in Indonesia. Therefore, this study aims to identify the most accurate forecasting model using the Autoregressive Integrated Moving Average (ARIMA) and Holt-Winters methods. Annual illiteracy rate data from 2011 to 2021 were analyzed using the Box-Jenkins and Exponential Smoothing approaches. The novelty of this study lies in the comparative evaluation of ARIMA and Holt-Winters models in forecasting national illiteracy rates. Model performance was assessed using Root Mean Square Error (RMSE) and Mean Square Error (MSE). The results indicate that ARIMA(0,0,1) is the best ARIMA model, while Holt-Winters with α = 0.8 and β = 0.9 provides the highest forecasting accuracy. Holt-Winters produced lower error values (RMSE = 0.33; MSE = 0.11) than ARIMA(0,0,1) (RMSE = 0.73; MSE = 0.54). This study contributes empirical evidence regarding the effectiveness of Holt-Winters for forecasting educational indicators and supports data-driven educational policy planning in Indonesia.]]>
Copyrights © 2026
