GR Semicolon EN

Show simple item record

dc.contributor.author
Timamopoulos, Christos
en
dc.date.accessioned
2020-06-16T11:47:54Z
dc.date.available
2020-06-17T00:00:35Z
dc.date.issued
2020-06-16
dc.identifier.uri
https://repository.ihu.edu.gr//xmlui/handle/11544/29631
dc.rights
Default License
dc.subject
Booking cancellations
en
dc.subject
Hospitality industry
en
dc.subject
Machine learning
en
dc.subject
Rare class mining
en
dc.subject
Anomaly detection
en
dc.title
Anomaly Detection: Predicting hotel booking cancellations
en
heal.type
masterThesis
en_US
heal.language
en
en_US
heal.access
free
en_US
heal.license
http://creativecommons.org/licenses/by-nc/4.0
en_US
heal.recordProvider
School of Science and Technology, MSc in Data Science
en_US
heal.publicationDate
2020-05-28
heal.abstract
Booking cancellations have a momentous impact on the hospitality industry, as regards to demand management. In order to diminish the influence of cancellations, hotels apply severe cancellation policies and tactics, that may have negative results on the hotel’s prestige and therefore its revenue. To minimize the impact of booking cancellations and improve the functionality of the hotel, a machine learning based model was developed. By using a dataset of a 4-stars hotel and approaching cancellation prediction as a supervised anomaly detection concept, it is exhibited that it is possible to develop a predicting machine learning model to forecast booking cancellations with overall accuracy 99%. The results of the research give the opportunity to the hotel manager to accurately predict demand through cancellations, produce improved forecasts and define better overbooking strategies.
en
heal.advisorName
Papadopoulos, Apostolos
en
heal.committeeMemberName
Papadopoulos, Apostolos
en
heal.committeeMemberName
Baltatzis, Dimitris
en
heal.committeeMemberName
Stavrinides, Stavros
en
heal.academicPublisher
IHU
en
heal.academicPublisherID
ihu
en_US


This item appears in the following Collection(s)

Show simple item record

Related Items