Analyzing the impact of COVID-19 on flight cancellation using machine learning and deep learning algorithms for a highly unbalanced dataset

Mohammed, Zaid; Asghar, Mamoona; Kanwal, Nadia

Abstract

Flight cancellations can be caused by many factors, including adverse weather conditions, and can result in lost money and time, etc. The COVID-19 pandemic has significantly exacerbated this situation, leading to a significant decrease in air travel. In 2020, the number of cancelled flights increased by 200% over 2019 and the number of flights decreased by 38%. This research focused on analyzing the impact of COVID-19 on flight cancellation using publicly available datasets from different locations. We looked further into the impact of class imbalance and techniques to reduce its effects on classification errors. The research was performed using four data sets, six re-sampling techniques, and 12 modeling algorithms. Random oversampling combined with random subsampling outperformed all other resampling techniques and multi-layer perceptron (MLP) was the best among all other machine learning models. For validation, we used the same resampling technique to two additional datasets namely income and diabetes datasets. The results showed that combining random oversampling with subsampling improved the accuracy of machine learning models.

Citation

Mohammed, Z., Asghar, M., & Kanwal, N. (2021, December). Analyzing the impact of COVID-19 on flight cancellation using machine learning and deep learning algorithms for a highly unbalanced dataset. Presented at 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), Cape Town, South Africa

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET)
• Start Date: Dec 9, 2021
• End Date: Dec 10, 2021
• Acceptance Date: Dec 9, 2021
• Publication Date: Dec 9, 2021
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Series Title: 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET)
• ISBN: 978-1-6654-4232-9
• DOI: https://doi.org/10.1109/ICECET52533.2021.9698693
• Keywords: deep learning; machine learning; class imbalance; SMOTE-Borderline; SMOTE-Tomek Links; SMOTE-ENN; Oversampling; Undersampling
• Public URL: https://keele-repository.worktribe.com/output/423523
• Publisher URL: https://ieeexplore.ieee.org/document/9698693