Predicting on-time departures: A comparison of static with dynamic Bayesian networks in the case of Newark Liberty International Airport

Tony Diana
Additional contact information
Tony Diana: Manager of the Outreach Division at Federal Aviation Administration, NextGen Collaboration and Messaging Office, USA

Journal of Airport Management, 2019, vol. 13, issue 3, 271-290

Abstract: This paper proposes to evaluate how a network of interrelated operational variables influence the percentage of on-time gate departures in the case of Newark Liberty International airport (EWR). It compared a static with a dynamic Bayesian network model to determine which one is the most likely to balance bias versus variance, which are two key elements in machine learning. Both models featured high variance and low bias, which limits generalisation beyond the training set. Nevertheless, both models stressed the significance of surface congestion in limiting the percentage of on-time gate departures, even when gate departure times are compared with those in the flight plan.

Keywords: Bayesian networks; taxi operations; punctuality; machine learning (search for similar items in EconPapers)
JEL-codes: M1 M10 R4 R40 (search for similar items in EconPapers)
Date: 2019
References: Add references at CitEc
Citations:

Downloads: (external link)
https://hstalks.com/article/550/download/ (application/pdf)
https://hstalks.com/article/550/ (text/html)
Requires a paid subscription for full access.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aza:jam000:y:2019:v:13:i:3:p:271-290

Access Statistics for this article

More articles in Journal of Airport Management from Henry Stewart Publications
Bibliographic data for series maintained by Henry Stewart Talks ().