Global Nominee

TimeFlies received a Global Nomination.

THE CHALLENGE: Clear for Take Off

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?


Our application predicts the likelihood of flight delays given the airport location, departure date and departure hour. Our system has two main nodes. We have a web server deployed using Spring Framework with a responsive design suitable for mobile devices. The magic happens in a Python calculation server implementing machine learning algorithms, which is able to estimate the probabilities of delaying.

The application is constantly taking data from the internet and updating the bayesian model in order to keep learning forever.

Resources Used
  • Flightview tracker
  • Forecast.io
  • NOAA
  • National Weather Service

  • JavaEE
  • Spring Framework
  • Gradle

  • Python
  • Scikit Learn - Naive Bayes Multiclass Clasification

  • HTML5
  • CSS3
  • Bootstrap
  • JavaScript
  • JQuery

Made inZaragoza Spain
from the minds of
How they did it