An E2E Data Science journey: Flight shopping made easy

Sorting flights by price is the default used by most online travel agencies and business travel management companies, but does it make sense for the travelers? Is price the most efficient ranking criterion?

At Egencia™, part of Expedia Group™, innovation is a key value, aiming to merge technology and traveler services for a better business travel management experience. We analyzed in depth Egencia users’ flight booking behaviour and we proved that there exists a better alternative to the default price-based sort.

In this meet-up we are going to discuss the transition from the classic price-based sort to a smarter sort, focusing mainly on:

• Two different ranking approaches: “Multi-criteria Decision Aid” and “Pointwise Learning to Rank”
• Offline evaluation and model selection
• Deployment and online evaluation

For a helicopter view of topics that are going to be covered, don’t hesitate to have a look at the following Medium article.

https://medium.com/expedia-group-tech/the-operations-research-behind-the-egencia-smartmix-flight-ranking-model-ebc9e0ba1fe0

petit disclamer pour nos inscrits français et/ou francophones, ce meet-up sera en anglais, mais venez quand même !

Our Speakers:

Wellington Bengtson (he/him/his)

Wellington works as a Senior Software Engineer at Egencia, the business travel brand by Expedia Group since December 2013. Prior to joining Expedia Group, Wellington worked for Amadeus, a travel technology company, also as a Software Engineer. He joined the Data Science team in September 2017 and since then, he has worked in diverse projects from data availability to model deployment. During his free time, Wellington likes to travel to rock festivals and to harbours where he meets his sailing friends.

Cristian Hedes (he/him/his)

Cristian works as a Data Scientist at Egencia, the business travel brand by Expedia Group, that he joined since his final-year internship in February 2018. He holds a Joint Master Degree in Information Technologies for Business Intelligence from CentraleSupélec Paris, The University of Tours and ULB (Université Libre de Bruxelles). After spending his student years in 6 different countries, working in the travel industry was the best choice to stay closer to the traveler’s mindset and settle down in Paris, a city he fell in love with. In his spare time, Cristian enjoys reconnecting with nature in a hiking trip, spending good times with friends and competing with himself in a night run.