Advertisement

Learning Cheap and Novel Flight Itineraries

  • Dmytro KaramshukEmail author
  • David Matthews
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11053)

Abstract

We consider the problem of efficiently constructing cheap and novel round trip flight itineraries by combining legs from different airlines. We analyse the factors that contribute towards the price of such itineraries and find that many result from the combination of just 30% of airlines and that the closer the departure of such itineraries is to the user’s search date the more likely they are to be cheaper than the tickets from one airline. We use these insights to formulate the problem as a trade-off between the recall of cheap itinerary constructions and the costs associated with building them.

We propose a supervised learning solution with location embeddings which achieves an AUC = 80.48, a substantial improvement over simpler baselines. We discuss various practical considerations for dealing with the staleness and the stability of the model and present the design of the machine learning pipeline. Finally, we present an analysis of the model’s performance in production and its impact on Skyscanner’s users.

Notes

Acknowledgement

The authors would like to thank the rest of the Magpie team (Boris Mitrovic, Calum Leslie, James Eastwood, Linda Edstrand, Ronan Le Nagard, Steve Morley, Stewart McIntyre and Vitaly Khamidullin) for their help and support with this project and the following people for feedback on drafts of this paper: Bryan Dove, Craig McIntyre, Kieran McHugh, Lisa Imlach, Ruth Garcia, Sri Sri Perangur, Stuart Thomson and Tatia Engelmore.

References

  1. 1.
    Ayhan, S., Samet, H.: Aircraft trajectory prediction made easy with predictive analytics. In: KDD, pp. 21–30 (2016)Google Scholar
  2. 2.
    Boyd, E.: The Future of Pricing: How Airline Ticket Pricing Has Inspired a Revolution. Springer, Heidelberg (2016)Google Scholar
  3. 3.
    Chamberlain, B.P., Cardoso, A., Liu, C.H., Pagliari, R., Deisenroth, M.P.: Customer life time value prediction using embeddings. In: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM (2017)Google Scholar
  4. 4.
    Colizza, V., Barrat, A., Barthélemy, M., Vespignani, A.: The role of the airline transportation network in the prediction and predictability of global epidemics. Proc. Nat. Acad. Sci. U.S.A. 103(7), 2015–2020 (2006)CrossRefGoogle Scholar
  5. 5.
    Etzioni, O., Tuchinda, R., Knoblock, C.A., Yates, A.: To buy or not to buy: mining airfare data to minimize ticket purchase price. In: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 119–128. ACM (2003)Google Scholar
  6. 6.
    Feng, S., Cong, G., An, B., Chee, Y.M.: POI2Vec: geographical latent representation for predicting future visitors. In: AAAI, pp. 102–108 (2017)Google Scholar
  7. 7.
    Fleurquin, P., Ramasco, J.J., Eguiluz, V.M.: Systemic delay propagation in the us airport network. Sci. Rep. 3, 1159 (2013)CrossRefGoogle Scholar
  8. 8.
    Guo, C., Berkhahn, F.: Entity embeddings of categorical variables. arXiv preprint arXiv:1604.06737 (2016)
  9. 9.
    Kejriwal, M., Szekely, P.: Neural embeddings for populated geonames locations. In: d’Amato, C., et al. (eds.) ISWC 2017. LNCS, vol. 10588, pp. 139–146. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-68204-4_14CrossRefGoogle Scholar
  10. 10.
    Liu, D.C., et al.: Related pins at pinterest: the evolution of a real-world recommender system. In: Proceedings of the 26th International Conference on World Wide Web Companion, pp. 583–592. International World Wide Web Conferences Steering Committee (2017)Google Scholar
  11. 11.
    Liu, S., Xiao, F., Ou, W., Si, L.: Cascade ranking for operational e-commerce search. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1557–1565. ACM (2017)Google Scholar
  12. 12.
    Liu, X., Liu, Y., Li, X.: Exploring the context of locations for personalized location recommendations. In: IJCAI, pp. 1188–1194 (2016)Google Scholar
  13. 13.
    Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111–3119 (2013)Google Scholar
  14. 14.
    Mottini, A., Acuna-Agost, R.: Deep choice model using pointer networks for airline itinerary prediction. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1575–1583. ACM (2017)Google Scholar
  15. 15.
    Pang, J., Zhang, Y.: DeepCity: a feature learning framework for mining location check-ins. arXiv preprint arXiv:1610.03676 (2016)
  16. 16.
    Perozzi, B., Al-Rfou, R., Skiena, S.: DeepWalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–710. ACM (2014)Google Scholar
  17. 17.
    Sculley, D., et al.: Hidden technical debt in machine learning systems. In: Advances in Neural Information Processing Systems, pp. 2503–2511 (2015)Google Scholar
  18. 18.
    Tata, S., et al.: Quick access: building a smart experience for Google drive. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1643–1651. ACM (2017)Google Scholar
  19. 19.
    Yan, B., Janowicz, K., Mai, G., Gao, S.: From ITDL to Place2Vec-reasoning about place type similarity and relatedness by learning embeddings from augmented spatial contexts. Proc. SIGSPATIAL 17, 7–10 (2017)Google Scholar
  20. 20.
    Zhao, S., Zhao, T., King, I., Lyu, M.R.: Geo-teaser: geo-temporal sequential embedding rank for point-of-interest recommendation. In: Proceedings of the 26th International Conference on World Wide Web Companion, pp. 153–162. International World Wide Web Conferences Steering Committee (2017)Google Scholar
  21. 21.
    Zhu, J., Shan, Y., Mao, J., Yu, D., Rahmanian, H., Zhang, Y.: Deep embedding forest: forest-based serving with deep embedding features. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1703–1711. ACM (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Skyscanner Ltd.EdinburghUK

Personalised recommendations