About
trivago is a global hotel search platform focused on reshaping the way travelers search for and compare hotels, while enabling advertisers of hotels to grow their businesses by providing access to a broad audience of travelers via our websites and apps. We provide aggregated information about the characteristics of each accommodation to help travelers to make an informed decision and find their ideal place to stay. Once a choice is made, the users get redirected to the selected booking site to complete the booking.
It’s in the interest of the traveler, advertising booking site, and trivago to suggest suitable accommodations that fit the needs of the traveler best to increase the chance of a redirect (clickout) to a booking site. We face a few challenges when it comes to recommending the best options for our visitors, so it’s important to effectively make use of the explicit and implicit user signals within a session (clicks, search refinement, filter usage) to detect the users’ intent as quickly as possible and to update the recommendations to tailor the result list to these needs.
Prizes
The best five teams will be rewarded with the following prizes:
Winner: |
8.000 Euro |
Second: |
4.000 Euro |
Third: |
2.000 Euro |
Fourth: |
1.000 Euro |
Fifth: |
1.000 Euro |
The Challenge
We’ve partnered with researchers from
TU Wien, Politecnico di Milano, and Karlsruhe Institute of Technology to launch the RecSys Challenge 2019, the annual data science challenge for the ACM Recommender Systems conference, to give developers, data scientists and anyone who’s interested the chance to work on real-world data science problems and large data sets. This year's challenge is to develop a session-based and context-aware recommender system to adapt a list of accommodations according to the needs of the user. In the challenge, participants will have to predict which accommodations have been clicked in the search result during the last part of a user session. Afterwards predictions are evaluated offline and scores will be displayed in a leaderboard. To this end, we have released a public dataset of hotel search sessions. Register here to download the dataset and start the challenge!
More information
More information about the challenge details regarding evaluation, metrics, submission format, etc. can be found on the dataset page and you will find all you need to know about the challenge timeline, workshop, paper submission and selection on the official RecSys Challenge website.
Details about partcipation
- To participate, you must register a team which consists of at least one person.
- Your entry in the challenge must include the source code. A third party should be able to use your submitted source to regenerate your results.
- Your source code must be released under an open-source license (Apache 2.0).
- As a condition to being awarded a Prize, a Prize winner must publish the final model’s software code and a paper which has to be published and presented at the Workshop on the RecSys Challenge 2019 in RecSys 2019 (Copenhagen).
License agreement/Terms and conditions
You can only participate in the challenge and download the Dataset if you accept the Terms and Conditions.
Credits
Challenge Organisers
- Phillip Monreal, trivago, Germany
- Wolfgang Gassler, trivago, Germany
- Jens Adamczak, trivago, Germany
- Gerard Leyson, trivago, Germany
- Peter Knees, TU Wien, Austria
- Yashar Deldjoo, Politecnico di Milano, Italy
- Farshad Bakhshandegan Moghaddam, Karlsruhe Institute of Technology, Germany
Advisors
- Dávid Zibriczky, DB Schenker, Germany
- Markus Schedl, Johannes Kepler University, Linz, Austria
- Hamed Zamani, University of Massachusetts Amherst, MA, USA
- Mehdi Elahi, Free University of Bozen, Bolzano
Behind the scenes @ trivago
- Andrea Chalmers, trivago, Germany
- Matthias Endler, trivago, Germany
- Melinda Kruse, trivago, Germany
- Lucie Ledoyen, trivago, Germany
- Daniel Riemer, trivago, Germany
- Selina Vermersch, trivago, Germany
- Anika Wolf, trivago, Germany