HOur Flight received a Global Nomination.
To comply with security and airline protocol, air travelers should arrive at the airport well in advance of their flight. Without realizing the probability of adverse conditions at the time of the scheduled departure, they may experience inconvenient delays at the airport. Delays can be short and relatively easy to manage, or they can cause long hours of waiting in crowded airports. Flight delays can even cause forced overnight stays at local hotels or inside the terminal. Travelers could benefit from knowing the likelihood of a delay as it could help them prepare for the wait time. Can an app be developed that predicts the impact of weather on airplane departure times?
We made an online application that provides user with information whether his flight is going to be delayed and why. Current predicition is based on the latest weather forecast at departure airport, but future iterations will consider weather on route and at arrival airport, as well as delays of connecting flights and total delays of airport traffic. Base for prediction is two-class boosted decision tree machine learning model. Prediction is further on improved by adding weighted values of above mentioned factors to obtained delay probability. This way our model explains additional variance in flight delays.
Predicting Flight Delays - D. Lawson, W. Castilo
Weather and Aviation - G. Kulesa
Bureau of Transportation Statistics
Microsoft Azure Machine Learning
Google: flight API, maps
Aviation Weather Centre - Terminal Aiport Forecast
Automated Weather Observing System - METAR