Bigdata Analysis on Airline Delay and Cancellation

Abstract

In recent years, there has been a tremendous increase in the number of air passengers. These increasing figures have enhanced problems, ultimately causing flight delays. Delay in flights is recognized not only the usual factor but also a bothersome experience offered to customers. These delays lead to loss of money to the travelers. Additionally, it also affects the business value and status of the aviation industry. The delays can be caused due to many factors like weather conditions, technical problem, air traffic etc. These concerned parameter makes it important in carrying out analysis based on past trends of delays which can be further divided into daily, monthly and yearly intervals. This project makes use of big data technologies like Apache Pig, hive and Hadoop Distributed File System (HDFS). These technologies would be helpful in determining delay problems faced by the aviation industry where an appropriate decision can be implemented and furthermore would be benefiting customers and industrialists of the aviation domain.