<![CDATA[Uncertainty in short-term investment decision-making. This study aims to analyze the daily stock price movement of PT Midi Utama Indonesia Tbk and to determine the feasibility of the ARIMA model for forecasting stock prices. The study employed a quantitative time series approach using daily closing price data over a 3-year period with daily frequency observations. The analysis was conducted using RStudio through descriptive statistics, stationarity testing, first-order differencing, ACF and PACF identification, ARIMA model selection, diagnostic testing, and forecast accuracy evaluation. The results indicate that the data were non-stationary at the level because the Augmented Dickey-Fuller test produced a p-value of 0.4372. After first differencing, the p-value decreased to 0.0100, indicating that the data had become stationary. The best model identified was ARIMA (1,1,1) because it had the lowest AIC value among the compared models. The Ljung-Box test yielded a p-value of 0.7116, indicating that there was no residual autocorrelation. The model produced an MAE of 6.10853, an RMSE of 8.97241, and a MAPE of 2.43817%, indicating that the model is highly accurate with an error rate below 8%. These findings demonstrate that the ARIMA (1,1,1) model is suitable for short-term forecasting of PT Midi Utama Indonesia Tbk stock prices.]]>
Copyrights © 2026
