<![CDATA[The high rate of dropout students in Indonesia remains a matter of considerable concern, as it erodes the quality of education and hinders the long-term development of human capital. The government of Indonesia has endeavored to address the issue of high dropout rates among students by implementing a range of initiatives. To demonstrate the effectiveness of this program, forecasting is necessary to measure and predict its outcomes. The purpose of this study is to utilize a time series approach, specifically the Autoregressive Integrated Moving Average (ARIMA) model, to predict the number of dropout students in the forthcoming years. This study employs a quantitative analysis using secondary data obtained from Statistics Indonesia (BPS) for the period 1970-2023. The ARIMA method is a statistical technique used to determine the most suitable forecasting model from historical data. This method has gained widespread popularity in the field of time series analysis due to its ability to manage non-stationary data effectively. The result shows that ARIMA (0,2,1) has the smallest AIC and meets the significant criteria model, also having the lowest MAPE value of 1.9%, indicating excellent forecasting accuracy. The plot of the result indicates a downward trend in the number of dropout students over the coming years. This downward trend aligns with the timeline of government interventions, suggesting a potential causal relationship between the implementation of educational support programs and the declining dropout rates. Thus, the prediction supports the effectiveness of these initiatives in mitigating dropout student in Indonesia.]]>
