This project focuses on analyzing AeroConnect’s historical passenger traffic data to uncover trends, forecast future demand, and provide actionable recommendations on which routes to invest in and which to scale back. I began by cleaning and preparing the dataset to ensure accuracy and consistency, then conducted exploratory data analysis to understand route patterns, growth trajectories, and seasonal behaviors. These insights guided my decision to use a SARIMA forecasting model, as it effectively captures both trends and seasonality in passenger traffic. After generating forecasts for the next 12 months, I compared projected demand with recent historical performance and calculated Compounded Monthly Growth Rates (CMGR) to measure past trends. Combining these insights, I classified routes into Invest (strong historical and forecasted growth) and Scale Back (consistent declines). My approach was to first understand the historical data, then leverage SARIMA forecasts, and finally integrate both perspectives to make holistic, data driven recommendations for AeroConnect’s strategic planning.
Link to cleaned CSV : https://drive.google.com/file/d/1E9WKAgKcS6jIavxADKRDWndAyLBr_15B/view?usp=sharing