Exploratory Data Analysis for Airline Disruption Management

TL;DR

This paper employs statistical and machine learning techniques to analyze airline disruption data, revealing key causes of irregular operations and validating modeling assumptions for disruption management.

Contribution

It introduces a combined macroscopic and microscopic analysis approach using basic statistics and machine learning on airline data, offering new insights into disruption causes.

Findings

Most irregular operations stem from flight delays

Turnaround times modeled as Gaussian processes

Validation of modeling assumptions for disruption management

Abstract

Reliable platforms for data collation during airline schedule operations have significantly increased the quality and quantity of available information for effectively managing airline schedule disruptions. To that effect, this paper applies macroscopic and microscopic techniques by way of basic statistics and machine learning, respectively, to analyze historical scheduling and operations data from a major airline in the United States. Macroscopic results reveal that majority of irregular operations in airline schedule that occurred over a one-year period stemmed from disruptions due to flight delays, while microscopic results validate different modeling assumptions about key drivers for airline disruption management like turnaround as a Gaussian process.