The ACM WSDM WebTour 2021 Challenge focuses on a multidestinations trip planning problem, which is a popular scenario in the travel domain. The goal of the challenge is to make the best recommendation of an additional trip destination. To encourage research on this field, Booking.com provided a unique dataset based on millions of real anonymized bookings. More than 800 participants have signed up for the contest. Best performing team achieved Accuracy @ 4 of 0.5939, using a blend of Transformers, GRUs, and feed-forward multi-layer perceptron. Additional leading teams implemented advanced state-of-the-art solutions to tackle the problem.
• Information systems → Personalization; Recommender systems.
Booking.com’s mission is to make it easier for everyone to experience the world. By investing in the technology that helps take the friction out of travel, Booking.com seamlessly connects millions of travelers with memorable experiences, a range of transport options, and incredible places to stay.
Many of the travelers go on trips that include more than one
destination. For instance, a user from the US could fly to Amsterdam
for 5 nights, then spend 2 nights in Brussels, 3 in Paris, and 1 in
Amsterdam again before heading back home. In this scenario, the
users are ofered personalized recommendations [
The goal of this challenge is to use a dataset based on millions
of real anonymized accommodation reservations to come up with
a strategy for making the best recommendation for their next
destination [
Reservation check-in date Reservation check-out date An anonymized ID of afiliate channel where the booker came from (e.g. direct, 3rd party referrals, paid search engine, etc.) desktop/mobile Country from which the reservation was made (anonymized) Country of the hotel (anonymized) city_id of the hotel’s city (anonymized) trip ID (a group of multi-destinations bookings within the same trip) 2
The dataset consists of over a million anonymized hotel reservations, based on real data, is available on the challenge website1 and described in table 1. Each reservation is a part of a customer’s trip (identified by utrip_id), which includes at least four consecutive reservations. There are 0 or more days between check-out and check-in dates of two consecutive reservations. The evaluation dataset is constructed similarly. However, the city_id of the final reservation of each trip is concealed and requires a prediction. 1https://www.bookingchallenge.com/
Test set release teams registration deadline
results submission deadline Announcement on the winners Paper submission deadline Paper notifications Camera ready submissions
3 4
Key dates of the challenge are listed in table 2.
The teams are expected to submit their top four cities predictions per each trip on the test set until January 28th 2021. The submission will be done in a csv file named submission.csv in the following format described in table 3: utrip_id represents each unique trip in the test, and the rest of the columns represent the city_id of the top four predicted cities. The top 10 teams will be invited to submit short papers (up to 4 pages + references in ACM sigconf format2). The papers will include the team and the authors names, an abstract, a text describing the method and the achieved score, and a link to their code repository and refer to the Booking.com challenge in the following format: Dmitri Goldenberg, Kostia Kofman, Pavel Levin, Sarai Mizrachi, Maayan Kafry, and Guy Nadav. 2021. Booking.com WebTour 2021 Challenge. http://www.bookingchallenge.com , In ACM WSDM Workshop on Web Tourism (WSDM WebTour’21), March 12th, 2021, Jerusalem, Israel.
Selected papers are expected to present their work in the workshop (in a virtual format). The submitted papers will be evaluated based on their clarity, novelty, and results presentation. Please contact wsdmchallenge@booking.com for any questions. 5
The goal of the challenge is to predict (and recommend) the final city (city_id) of each trip (utrip_id). The quality of the predictions is evaluated based on the top four recommended cities for each trip
mbaigorria
aprec hakubishin3 & u++ & yu-y4
testing Alexander Makeev
YiNet Marlesson - MARS-Gym by using Top-4 Accuracy metric (4 representing the four suggestion slots at Booking.com website). When the true city is one of the top 4 suggestions (regardless of the order), it is considered correct. 6
To encourage research contributions, the top three performing teams will receive Booking.com Travel Credits. The best paper team will receive an additional prize. Paper submission and virtual participation at the workshop are mandatory in order to be eligible for a prize. 7
820 participants have signed up for the challenge. After two months of a contest, 97 of them performed a final submission, grouped in 40 competing teams. Top 10 performing teams are listed in table 4. The best performing team achieved Accuracy @ 4 of 0.5939, implementing a blend of 3 diferent neural network architectures, using Transformers, GRUs, and feed-forward MLP. Other solutions relied on Eficient Manifold Density Estimator, LSTM networks, Attention mechanisms, Lambdarank, and further state-of-the-art methods. The teams have submitted short papers and code repositories with a detailed description of their solution methodology.