Predicting the status of flights using data analysis and machine learning

Abstract

As the travel industry grows, so do the demanding aspects of air transport. The accuracy of flight status is critical to the travelling experience of passengers, the scheduling of airlines and the cost of airport operations. Most of the airports nowadays are forecasting flight routes to make airport scheduling more accurate, save time and cost, and improve travellers' experience. The use of data analytics and machine learning to predict multiple flight states will significantly improve the accuracy of the results and satisfy the needs of travellers, airlines and airport operations to a greater extent. This thesis will show how to use data analytics combined with machine learning models for flight status analysis and explain the conclusions.