Data-driven Modeling of Airlines Pricing

The popularity of travelling by airplanes is constantly growing. Much of existing research describe the global flight market. At the same time, Russian air market is characterized by its peculiarities that have to be identified to build proper models of airfare. The objective of this study is to analyze Russian air transportation market and compare the behavior of prices on local and global flights. Using these data, collected from two independent ticket price information aggregators (AviaSales and Sabre) for the period of spring-summer 2015, an empirical data-driven model was built for air prices prediction for different flight directions. We found that the form of price dependency on purchase earliness differs dramatically between local and international flights in two largest Russian cities (Moscow and Saint-Petersburg).