Flight Delay Prediciton at an Airport Using Maching Learning

摘要

The increasing demand for air transportation makes the problem of flight delays increasingly prominent. Accurate prediction of flight delays is of great significance to passengers' travel and the operation of airlines. In this paper, we establish a flight delay prediction model to predict the departure delay of Newark Liberty International Airport based on Catboost algorithm. The result shows that the prediction accuracy of our model can reach 0.77. In addition, we also analyze the contribution of each feature in the prediction by using SHAP.