ChangiNOW : a mobile application for efficient taxi allocation at airports

Abstract

The important role that taxis play in bringing passengers from an airport terminal to their final destination is often overlooked in airport operations and design. Due to varying flight arrival patterns at different terminals, taxi drivers are often unsure which terminal they should queue at. In this thesis, we present ChangiNOW, a mobile app that uses a predictive queueing model to efficiently allocate taxis. The ChangiNOW system uses observed taxi and flight data at each of the four terminals of Singapores Changi Airport to estimate the expected waiting time and queue length for taxis arriving at these terminals, and then sends taxis to terminals where waiting time is shortest. The app communicates this information to taxi drivers in a visually intuitive and appealing way, motivating them to service those terminals with the highest taxi demand. We present the theoretical details that underpin our prediction engine and validate our theory with several targeted numerical simulations. Finally, we evaluate the performance of this system in large-scale experiments and show that our system achieves a significant improvement in both passenger and taxi waiting time.