<![CDATA[This study examines the application of the Autoregressive Integrated Moving Average (ARIMA) method in forecasting the stock price of Meta Platforms Inc. (META) using historical time series data from 2021 to 2025. The main objective is to identify the best-fit ARIMA model and evaluate its predictive accuracy in capturing stock price dynamics. Data preprocessing was conducted through differencing to achieve stationarity, followed by model identification using autocorrelation and partial autocorrelation analysis. Among several candidate models, ARIMA (2, 2, 1) was selected as the most appropriate, supported by the lowest Akaike’s Information Criterion (AIC) value of 530.9496 and favorable diagnostic tests. Residual analysis indicated no significant autocorrelation and normally distributed errors, confirming the model’s adequacy. Further accuracy evaluation demonstrated that ARIMA (2, 2, 1) achieved the lowest Root Mean Squared Error (RMSE) of 32.49 and Mean Absolute Percentage Error (MAPE) of 7.07%, indicating reliable forecasting performance. These findings underscore the effectiveness of ARIMA in modeling linear stock price patterns and offer valuable insights for investors and analysts in short- to medium-term decision-making. The practical significance of forecasting META’s stock price lies in the company’s strategic position within the global technology ecosystem, where accurate predictions serve as a crucial foundation for risk management, portfolio development, and policy formulation in highly volatile markets. Nevertheless, limitations persist, as ARIMA is unable to account for nonlinear dynamics or external shocks. Future studies are recommended to integrate hybrid models, such as ARIMA-LSTM, or macroeconomic indicators to enhance forecasting accuracy.]]>
