Publication

Abstract : The prediction of flight delay can be considered as one of the most challenging problems to solve. Delay of an aircraft is not only a problem for an airline but also for the passengers. Flights can be delayed due to several reasons, the weather being the primary one. In this paper, our focus is to predict the delay of the flights due to bad weather. The dataset used consists of flight data from JFK airport from the sources Bureau of Transportation statistics and weather data from the National Centers for Environmental Information. The results of different machine learning algorithms like Linear Regression, SVR, Decision Tree Regressor, Random Forest Regressor, Ridge, and Lasso Regressor, for prediction of flight delay, are compared. XGboost regressor had the best performance in all the scenarios with least RMSE score of 0.81.