Lost and found: predicting airline baggage at-risk of being mishandled

H. van Leeuwen; Yingqian Zhang; Kalliopi Zervanou; Shantanu Mullick; Uzay Kaymak; Tom de Ruijter

Lost and found: predicting airline baggage at-risk of being mishandled

H. van Leeuwen, Yingqian Zhang, Kalliopi Zervanou, Shantanu Mullick, Uzay Kaymak, Tom de Ruijter

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

28 Downloads (Pure)

Abstract

The number of bags mishandled while transferring to a connecting flight is high. Bags at-risk of missing their connections can be processed faster; however, identifying such bags at-risk is still done by simple business rules. This work researches a general model of baggage transfer process and proposes a complex prediction model for identifying the bags at-risk. Our prediction model is compared to the current rule based method and a benchmark using logistic regression. The results show that our model offers an increase in accuracy coupled with a marked increase in precision and recall when identifying bags that are transferred unsuccessfully.

Original language	English
Title of host publication	Proceedings of the International Conference on Agents and Artificial Intelligence
Publication status	Accepted/In press - Dec 2019

Fingerprint

Cite this

van Leeuwen, H., Zhang, Y., Zervanou, K., Mullick, S., Kaymak, U., & de Ruijter, T. (Accepted/In press). Lost and found: predicting airline baggage at-risk of being mishandled. In Proceedings of the International Conference on Agents and Artificial Intelligence

@inproceedings{52cb54441c9442ab96fa7db70de140c2,

title = "Lost and found: predicting airline baggage at-risk of being mishandled",

abstract = "The number of bags mishandled while transferring to a connecting flight is high. Bags at-risk of missing their connections can be processed faster; however, identifying such bags at-risk is still done by simple business rules. This work researches a general model of baggage transfer process and proposes a complex prediction model for identifying the bags at-risk. Our prediction model is compared to the current rule based method and a benchmark using logistic regression. The results show that our model offers an increase in accuracy coupled with a marked increase in precision and recall when identifying bags that are transferred unsuccessfully.",

author = "{van Leeuwen}, H. and Yingqian Zhang and Kalliopi Zervanou and Shantanu Mullick and Uzay Kaymak and {de Ruijter}, Tom",

year = "2019",

month = "12",

language = "English",

booktitle = "Proceedings of the International Conference on Agents and Artificial Intelligence",

}

Lost and found : predicting airline baggage at-risk of being mishandled. / van Leeuwen, H.; Zhang, Yingqian ; Zervanou, Kalliopi ; Mullick, Shantanu ; Kaymak, Uzay; de Ruijter, Tom.

Proceedings of the International Conference on Agents and Artificial Intelligence. 2019.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Lost and found

T2 - predicting airline baggage at-risk of being mishandled

AU - van Leeuwen, H.

AU - Zhang, Yingqian

AU - Zervanou, Kalliopi

AU - Mullick, Shantanu

AU - Kaymak, Uzay

AU - de Ruijter, Tom

PY - 2019/12

Y1 - 2019/12

N2 - The number of bags mishandled while transferring to a connecting flight is high. Bags at-risk of missing their connections can be processed faster; however, identifying such bags at-risk is still done by simple business rules. This work researches a general model of baggage transfer process and proposes a complex prediction model for identifying the bags at-risk. Our prediction model is compared to the current rule based method and a benchmark using logistic regression. The results show that our model offers an increase in accuracy coupled with a marked increase in precision and recall when identifying bags that are transferred unsuccessfully.

AB - The number of bags mishandled while transferring to a connecting flight is high. Bags at-risk of missing their connections can be processed faster; however, identifying such bags at-risk is still done by simple business rules. This work researches a general model of baggage transfer process and proposes a complex prediction model for identifying the bags at-risk. Our prediction model is compared to the current rule based method and a benchmark using logistic regression. The results show that our model offers an increase in accuracy coupled with a marked increase in precision and recall when identifying bags that are transferred unsuccessfully.

M3 - Conference contribution

BT - Proceedings of the International Conference on Agents and Artificial Intelligence

ER -

Access to Document

ICAART_2020_141_CR-2Final author version , 203 KB