Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?

<p>Using 27 million flight bookings for 2 years from a major international airline company, we built a Next Likely Destination model to ascertain customers’ next flight booking. The resulting model achieves an 89% predictive accuracy using historical data. A unique aspect of the model is the i...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Saravanan Thirumuruganathan (11038038) (author)
مؤلفون آخرون: Soon-gyo Jung (7434773) (author), Dianne Ramirez Robillos (14151015) (author), Joni Salminen (7434770) (author), Bernard J. Jansen (7434779) (author)
منشور في: 2021
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513567901876224
author Saravanan Thirumuruganathan (11038038)
author2 Soon-gyo Jung (7434773)
Dianne Ramirez Robillos (14151015)
Joni Salminen (7434770)
Bernard J. Jansen (7434779)
author2_role author
author
author
author
author_facet Saravanan Thirumuruganathan (11038038)
Soon-gyo Jung (7434773)
Dianne Ramirez Robillos (14151015)
Joni Salminen (7434770)
Bernard J. Jansen (7434779)
author_role author
dc.creator.none.fl_str_mv Saravanan Thirumuruganathan (11038038)
Soon-gyo Jung (7434773)
Dianne Ramirez Robillos (14151015)
Joni Salminen (7434770)
Bernard J. Jansen (7434779)
dc.date.none.fl_str_mv 2021-01-13T06:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s10660-021-09457-0
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Forecasting_the_nearly_unforecastable_why_aren_t_airline_bookings_adhering_to_the_prediction_algorithm_/21597231
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Commerce, management, tourism and services
Air transportation and freight services
Information and computing sciences
Artificial intelligence
Data management and data science
Human-centred computing
Machine learning
Prediction
Recommendation
Airlines
Travel
User evaluation
dc.title.none.fl_str_mv Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Using 27 million flight bookings for 2 years from a major international airline company, we built a Next Likely Destination model to ascertain customers’ next flight booking. The resulting model achieves an 89% predictive accuracy using historical data. A unique aspect of the model is the incorporation of self-competence, where the model defers when it cannot reasonably make a recommendation. We then compare the performance of the Next Likely Destination model in a real-life consumer study with 35,000 actual airline customers. In the user study, the model obtains a 51% predictive accuracy. What happened? The Individual Behavior Framework theory provides insights into possibly explaining this inconsistency in evaluation outcomes. Research results indicate that algorithmic approaches in competitive industries must account for shifting customer preferences, changes to the travel environment, and confounding business effects rather than relying solely on historical data.</p><h2>Other Information</h2> <p> Published in: Electronic Commerce Research<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1007/s10660-021-09457-0" target="_blank">http://dx.doi.org/10.1007/s10660-021-09457-0</a></p>
eu_rights_str_mv openAccess
id Manara2_208e7b95a7bde7a40246721b5245c021
identifier_str_mv 10.1007/s10660-021-09457-0
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/21597231
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?Saravanan Thirumuruganathan (11038038)Soon-gyo Jung (7434773)Dianne Ramirez Robillos (14151015)Joni Salminen (7434770)Bernard J. Jansen (7434779)Commerce, management, tourism and servicesAir transportation and freight servicesInformation and computing sciencesArtificial intelligenceData management and data scienceHuman-centred computingMachine learningPredictionRecommendationAirlinesTravelUser evaluation<p>Using 27 million flight bookings for 2 years from a major international airline company, we built a Next Likely Destination model to ascertain customers’ next flight booking. The resulting model achieves an 89% predictive accuracy using historical data. A unique aspect of the model is the incorporation of self-competence, where the model defers when it cannot reasonably make a recommendation. We then compare the performance of the Next Likely Destination model in a real-life consumer study with 35,000 actual airline customers. In the user study, the model obtains a 51% predictive accuracy. What happened? The Individual Behavior Framework theory provides insights into possibly explaining this inconsistency in evaluation outcomes. Research results indicate that algorithmic approaches in competitive industries must account for shifting customer preferences, changes to the travel environment, and confounding business effects rather than relying solely on historical data.</p><h2>Other Information</h2> <p> Published in: Electronic Commerce Research<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1007/s10660-021-09457-0" target="_blank">http://dx.doi.org/10.1007/s10660-021-09457-0</a></p>2021-01-13T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s10660-021-09457-0https://figshare.com/articles/journal_contribution/Forecasting_the_nearly_unforecastable_why_aren_t_airline_bookings_adhering_to_the_prediction_algorithm_/21597231CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/215972312021-01-13T06:00:00Z
spellingShingle Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?
Saravanan Thirumuruganathan (11038038)
Commerce, management, tourism and services
Air transportation and freight services
Information and computing sciences
Artificial intelligence
Data management and data science
Human-centred computing
Machine learning
Prediction
Recommendation
Airlines
Travel
User evaluation
status_str publishedVersion
title Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?
title_full Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?
title_fullStr Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?
title_full_unstemmed Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?
title_short Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?
title_sort Forecasting the nearly unforecastable: why aren’t airline bookings adhering to the prediction algorithm?
topic Commerce, management, tourism and services
Air transportation and freight services
Information and computing sciences
Artificial intelligence
Data management and data science
Human-centred computing
Machine learning
Prediction
Recommendation
Airlines
Travel
User evaluation