Analysis of Flight Delay and Cancellation Prediction Based on Machine Learning Models

Flight delay and cancellation are inevitable and they often lead to concern in passengers as well as profit loss of the airlines and airports. An accurate estimation of flight delays and cancellation is critical for airlines because the results can be applied to increase customer satisfaction and income of airline agencies. This paper proposed several machine learning models on a dataset containing flight information from 2018. These models are compared by using receiver operating characteristic curves and learning curves to determine which model best fits the data.