eduzhai > Applied Sciences > Transportation >

Prediction of Airline Delays Using K-Nearest Neighbor Algorithm

  • Save

... pages left unread,continue reading

Document pages: 4 pages

Abstract: According to the Bureau of Transportation Statistics, approximately twenty percent of the entire scheduled commercial flights are delayed. Airlines cause multi-billion dollars per year and cause great inconvenience to passengers. The primary goal of the model is to predict airline delays caused by inclement weather conditions using supervised machine learning algorithms. US domestic flight data and the weather data from 2013 to 2015 were extracted and used to train the model. K-Nearest Neighbors is implemented to build model which can predict delays of individual flights. In the prediction step flight schedule and weather data for the year 2016 were gathered and fed into the model. Using those data, the trained model performed a binary classification to predict whether a scheduled flight will be delayed or on-time.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×