Analysis and Forecasting of International Airport Traffic Volume

Globalization has resulted in increases air transportation demand and passenger traffic. With the traffic, airports face challenges related to infrastructure, services, future development. Air traffic forecasting is essential ensuring appropriate investment airports. In this study, we combined fuzzy theory with support vector regression (SVR) develop a SVR (FSVR) model for international airport This was used predict volumes at world’s 10 busiest terms of 2018. The predictions were made period from August 2014 December 2019. For time series, developed FSVR can consider historical changes. suitably divide changes into sets, generate membership function values, establish relations produce interpolated values minimal errors. Thus, prediction continuous data, data smallest errors be subjected find optimal hyperplane minimum distance sample points. performance proposed compared those five other models. Of models, exhibited lowest mean absolute percentage error (MAPE), error, root square all types analyzed; MAPE below 2.5. growth trends flows, aircraft logistics. An authority use analyze existing operational facilities service capacity, bottlenecks operations, create blueprint findings revealed that implementing hybrid modeling approach, specifically model, significantly enhance model. allows airlines patterns, identify viable new destinations, optimize their schedules or fleet, make accurate marketing decisions, plan effectively. guide timely construction predictions. Rapid, cost-effective, efficient, balanced planning enables provision fast, comfortable, safe, convenient cargo services while proper airport’s capacity land-side connections.