Applications of Business Analytics in Predicting Flight On-time Performance in a Complex and Dynamic System

Citation metadata

Date: Winter 2018
From: Transportation Journal(Vol. 57, Issue 1)
Publisher: American Society of Transportation and Logistics, Inc.
Document Type: Report
Length: 9,155 words
Lexile Measure: 1390L

Document controls

Main content

Article Preview :

Abstract

Flight on-time performance is one of the most important issues in the National Airspace System, a very complex and dynamic system. To avoid negative impacts to the aviation industry, the Federal Aviation Administration has set a long-term objective of understanding and mitigating flight delays. Building an effective and accurate prediction model of flight-delay incidents will help airport executives make the best decisions in delay scenarios. This article utilized two advanced prediction methods to predict the probability of a flight-delay incident--data mining using the decision tree and data mining using Bayesian inference. Prediction models were built using flight on-time performance data collected from different sources. The results indicated important airport-related factors and their effects on the flight on-time performance.

Keywords

Flight on-time performance, flight delays, national airspace system, business analytics, data mining, decision trees, Bayesian inference

**********

The Federal of Aviation Administration (FAA) defines the National Airspace System (NAS) as "the network of United States airspace to include air navigation facilities, equipment, services, airports or landing areas, aeronautical charts, information/services, rules, regulations, procedures, technical information, manpower, and material" (FAA 2012). As one of the largest and most complex stochastic systems in the world, NAS consists of a number of people, procedures, facilities, and equipment needed to facilitate safe and on-time air travel in the United States and over the world. A flight through the NAS typically begins and ends at an airport and involves numerous interrelated components, such as administration, air-traffic controllers, airports, airport facilities, airlines, aircraft, and passengers. The complexity of the NAS and uncertainties existing in its components create great difficulties in predicting incidents in the system.

Flight on-time performance is one of the most serious issues in NAS. The air travel demand has increased significantly over the years and put US airports at their capacity limit, thereby increasing the importance of on-time flights. Understanding and mitigating flight delays in NAS is a major long-term objective of the FAA. Airlines for America (2014a) reported strong air travel demand with approximately 42 million passengers flying between December 17, 2014, and January 4, 2015. Daily passenger volumes during that period are expected to range from 2 million to 2.35 million. As the demand for air travel increases, on-time performance becomes very important to the aviation industry. Flight delays are a nuisance for any air traveler and have negative economic impacts. According to the Congress Joint Economic Committee (2008), it was estimated that flight delays cost $40 billion per year in the United States alone. In 2014, Airlines for America estimated the per-minute-cost of delays to US airlines was $81.18 per minute, 2.7 percent greater than in 2013, resulting in a total of $9.15 billion in direct aircraft operating costs (Airlines for America 2014b).

The statistics show the significance of flight on-time performance issues and how they affect the aviation industry. Prediction of delay incidents and identification of impact factors will allow airport executives to make critical decisions for mitigation of risks and increasing the percentage of on-time flights. Flight on-time performance...

Source Citation

Source Citation   

Gale Document Number: GALE|A526996445