A Transportation Analytic Solution for Predicting Flight Cancellations

Abstract

Flight cancellations can negatively impact passengers and airlines by causing stress, time loss, financial losses, and providing a disruptive travelling experience. Airlines pay for crewmembers, provide refunds for passengers, and need to account for other unexpected expenses. Passengers might have a connection and need to get to a specific place for an important event such as a work conference, wedding, funeral, or vacation. Applying advanced transportation data analytical techniques to develop practical solutions can contribute to the ongoing development of more efficient and reliable air travel. In this paper, we present a data science solution, which integrates flight data, weather data, and other related data to determine key factors contributing to flight cancellations. In particular, we focus on weather-related factors such as precipitation and wind speed. Evaluation results on real data show the practicality and accuracy of our solution in predicting flight cancellations.