<![CDATA[Increased interest among Indonesians in investing in a single financial asset has driven significant growth in the capital market. However, high market volatility brings the risk of loss that needs to be anticipated. One of the relevant models in dealing with these problems is using the nonlinear Exponential Smooth Transition Autoregressive (ESTAR) model. ESTAR is an extension of the Autoregressive (AR) model that uses smoother transitions to handle nonlinear time series data. This study aims to predict stock prices using the ESTAR nonlinear model to help investors deal with market uncertainty and manage short-term risk. The data used is the daily closing price of PT Bank Central Asia Tbk shares, for the period January 2022 to December 2024. The research methodology includes stationarity test, AR(p) parameter estimation, ESTAR(p,d) model parameter estimation, and prediction accuracy evaluation using Mean Absolute Percentage Error (MAPE). The results show that the AR(1) model is the best order model and the ESTAR(1,1) model is the final optimal model. Evaluation of the prediction results for the next one month period, shows that the MAPE value is 2.79% which indicates the model's performance in predicting stock prices is very good.]]>
Copyrights © 2025
