FlyOnTime

Global Nominee

FlyOnTime received a Global Nomination.

THE CHALLENGE: Clear for Take Off
Aeronautics

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?

Explanation

Our App uses the past weather and flight data from the last 20 years and learns the patterns and relations between the weather parameters at hundreds of airports and the flight departure/arrival delays.

It then uses machine learning to classify and predict the future flight departure/arrival time delays after getting trained on a real big data-set.

The front end is an android app interface that asks the user for his location and flight schedule and passes the information to the back end script that runs a classification algorithm to re-learn and predict the data for his flight. This data is sent back to the user as an approximation of how late his flight would be.


Resources Used

1) DarkSky forecast API [https://developer.forecast.io/]

2) US Bureau of Transportation Statistics ( Department of Transportation ) [www.transtats.bts.gov]

3) Iowa environmental Mesonet ( Past Weather data for each airport/city) [https://mesonet.agron.iastate.edu/request/download...]

4) R studio libraries (e1071,) inbuilt libraries for classification ( naiveBayes,Kmeans)

5) Android Studio , Php, Python for the front end


Made inBangalore India
from the minds of
How they did it