<![CDATA[The stock price movement of Apple Inc. (AAPL) exhibits high levels of fluctuation and volatility, necessitating adaptive forecasting methods to assist investors in decision-making. This study aims to implement the Single Exponential Smoothing (SES) method to predict the closing price of AAPL stock based on historical data. The research methodology involves processing 1,256 daily data points from Investing.com for the period October 2020 to October 2025 using the Python programming language. The results indicate that using a smoothing parameter of $\alpha = 0.9$ yields the most optimal performance with a Mean Absolute Percentage Error (MAPE) of 1.29% and a Mean Absolute Error (MAE) of $2.2267. With a MAPE value below 10%, the accuracy of this model is classified as Highly Accurate. The system generates an estimated AAPL stock price for the next period of $258.87, proving that the SES method is effective for short-term forecasting on volatile data]]>
Copyrights © 2026
