Forecasting the Weekly Stock Price of Apple Inc. (AAPL) using Autoregressive Integrated Moving Average Method

Abstract

The stock price of Apple Inc. (AAPL) has been a subject of significant interest due to its volatility and market dynamics. In this study, we aimed to forecast the stock price of Apple Inc. from April 10, 2024-April 10, 2025, using the ARIMA(0,1,3) model. This model was selected due to its ability to capture key patterns in the time series data while minimizing forecasting errors. After differencing the data to ensure stationarity, the ARIMA model was fitted, incorporating two autoregressive (AR) terms and two moving average (MA) terms. Residual analysis, including the Ljung-Box and Shapiro-Wilk tests, confirmed that the residuals were uncorrelated and normally distributed, validating the model's appropriateness. The ARIMA(0,1,3) model produced reliable forecasts with minimized error metrics, offering a robust method for short-term stock price predictions. This study demonstrates the potential of ARIMA models in financial forecasting, particularly in predicting stock prices with a reasonable degree of accuracy.