A Data Mining Approach to Flight Arrival Delay Prediction for American Airlines

TL;DR

This paper presents a data mining and machine learning approach, specifically using gradient boosting, to predict flight delays for American Airlines, aiming to improve punctuality and reduce operational losses.

Contribution

It introduces a predictive model for flight delays using data mining techniques, with hyper-parameter tuning achieving high accuracy for American Airlines' domestic flights.

Findings

Gradient Boosting Classifier achieved 85.73% accuracy.

Model effectively predicts flight delays for top US airports.

Data-driven approach can enhance airline punctuality management.

Abstract

In the present scenario of domestic flights in USA, there have been numerous instances of flight delays and cancellations. In the United States, the American Airlines, Inc. have been one of the most entrusted and the world's largest airline in terms of number of destinations served. But when it comes to domestic flights, AA has not lived up to the expectations in terms of punctuality or on-time performance. Flight Delays also result in airline companies operating commercial flights to incur huge losses. So, they are trying their best to prevent or avoid Flight Delays and Cancellations by taking certain measures. This study aims at analyzing flight information of US domestic flights operated by American Airlines, covering top 5 busiest airports of US and predicting possible arrival delay of the flight using Data Mining and Machine Learning Approaches. The Gradient Boosting Classifier Model is deployed by training and hyper-parameter tuning it, achieving a maximum accuracy of 85.73%. Such an Intelligent System is very essential in foretelling flights'on-time performance.