Business Forecasting: Airline Visitor Data Analysis Case Study

This case study analyzes time series data of German visitor arrivals to Australia, spanning from January 1999 to February 2019, to forecast future visitor numbers for an airline. The analysis begins with identifying the time series, followed by an examination of its characteristics, including trend and seasonality. The study confirms the presence of systematic components using the Augmented Dickey-Fuller test. It then explores economic and environmental factors influencing the series, such as income and transportation costs. The data is smoothed using a weighted moving average in Excel to identify underlying components. The results are presented graphically, comparing original and smoothed series. The study then applies AR(1) model, diagnoses it, and forecasts monthly visitor arrivals for one year beyond the sample period, comparing the results with Minitab forecasts. Finally, it evaluates the model's appropriateness and discusses factors for long-term forecasting.