Booking.com @ RecSys 2022
Booking.com’s publications at the 16th ACM conference on Recommender Systems
Booking.com’s mission is to make it easier for everyone to experience the world. We invest in the technology that helps take the friction out of travel, and we seamlessly connect millions of travelers with memorable experiences, transportation options and incredible places to stay. To reach this goal, we personalize the experience for each of our customers that uses our products. We’re glad to announce that Booking.com is a gold sponsor of ACM RecSys 2022 in Seattle. Check out the work we do on Recommender Systems and will be presented at the conference.
Personalizing Benefits Allocation Without Spending Money
Dima Goldenberg, Javier Albert
Modern e-commerce platforms make use of promotional offers such as discounts and rewards to encourage customers to complete purchases. While offering the promotions has a great effect on the sales, it also generates a monetary loss. By utilizing causal machine learning and optimization, our team at Booking.com was able to personalize the promotions allocation to customers, while efficiently controlling the spend within a given budget.
In this talk we’ll share the personalized promotion assignment techniques, such as uplift modeling and constrained optimization, which helped us to predict the outcomes of discounts offering and allocate them efficiently. This solution allowed us to unlock promotional campaigns to bring more value to the customers and grow our business.
Democratizing Personalization within a Central Recommendation Platform
Chana Ross, Tomer Ovadia, Jake Mooney, Amit Meitin, Eytan Kabilou, Mush Kabalo, and Dima Goldenberg
Recommender systems play a crucial role in e-commerce platforms, reducing the information overload problem by providing and prioritizing relevant information based on a user’s implicit and explicit preferences. Large e-commerce platforms often rely on a multitude of machine learning models at the same time to optimize the many aspects of the site that can be improved. Occasionally there are duplicate recommender systems that solve a similar or even the same recommendation task, a situation often caused by
evolving business objectives, use-case constraints or even just a lack of synchronicity between teams of a large organization. In this work we demonstrate a centralized Recommendation Platform at Booking.com — one of the world’s leading online travel platforms. The system is created to reduce the duplication of work, provide utilities for authors of new recommendation models, increase impact by accelerating adoption of better solutions to common recommendation problems, and serve as a single, trusted point of access for recommendations across the website. It allows us to democratize the usage of recommendations across the company and ease the development of new sophisticated models. This, in turn, allows standardization of recommendations tasks and increases the adoption of recommendation systems by various product teams, to bring a personalized experience to each of our customers.
Extending Open Bandit Pipeline to Simulate Industry Challenges
Bram van den Akker, Niklas Weber, Felipe Moraes, and Dima Goldenberg
Bandit algorithms are often used in the e-commerce industry to train Machine Learning (ML) systems when pre-labeled data is unavailable. However, the industry setting poses various challenges that make implementing bandit algorithms in practice non-trivial. In this paper, we elaborate on the challenges of off-policy optimisation, delayed reward, concept drift, reward design, and business rules constraints that practitioners at Booking.com encounter when applying bandit algorithms.
Our main contributions is an extension to the Open Bandit Pipeline (OBP) framework. We provide simulation components for some of the above-mentioned challenges to provide future practitioners, researchers, and educators with a resource to address challenges encountered in the e-commerce industry.
RecSys Workshop on Recommenders in Tourism
RecTour ’22 Workshop — Dima Goldenberg
This full-day workshop held in conjunction with ACM RecSys 2022 addresses specific challenges for recommender systems in the tourism domain. Planning a vacation usually involves searching for a set of products that are interconnected (e.g., transportation, lodging, attractions) with limited availability, and where contextual aspects may have a major impact (e.g., time, location, weather). RecTour 2022 aims at attracting presentations of novel ideas in order to advance the current state of the art in the field of tourism recommenders; topics include specific applications and case studies (evaluation), specific methods and techniques, context and mobility, the cold-start problem, preference elicitation, and emotions and recommenders. Researchers and practitioners from different fields are invited to submit research and position papers, project ideas as well as demonstration systems.
Previous Booking.com work on Recommender Systems
Recommenders systems are key components of Booking.com ML portfolio. Check out our previous publications on the subject:
- Simulations in Recommender Systems : An Industry Perspective Lucas Bernardi, Sakshi Batra, Cintia Bruscantini -SimuRec’ 21 Workshop
- Optimization Levers for Promotions Personalization Under Limited Budget Dima Goldenberg, Javier Albert, Guy Tsype -MORS’21 Workshop
- I Know What You Did Next Summer: Challenges in Travel Destination Recommendation Dima Goldenberg, Sarai Mizrachi, Adam Horowitz, Ioannis Kangas, Or Levkovich, Alessandro Mozzato, Maud Schwoerer, Michele Ferretti, Panagiotis Korvesis, Lucas Bernardi -RecTour ’21 Workshop
- Recommender Systems for Personalized User Experience: Lessons learned at Booking.com Ioannis Kangas, Maud Schwoerer, Lucas Bernardi -RecSys’21
- Free Lunch! Retrospective Uplift Modeling for Dynamic Promotions Recommendation within ROI Constraints
Dima Goldenberg, Javier Albert, Lucas Bernardi, Pablo Estevez- RecSys ‘20 - 150 Successful Machine Learning Models: 6 Lessons Learned at Booking.com
Lucas Bernardi, Themis Mavridis, Pablo Estevez- KDD ‘19 - Booking.com Challenge
Dima Goldenberg, Kostia Kofman, Pavel Levin, Sarai Mizrachi, Maayan Kafry, Guy Nadav- WebTour @ WSDM ‘21 - Combining Context Features in Sequence-Aware Recommender Systems Sarai Mizrachi, Pavel Levin — RecSys ‘19
- Beyond algorithms: Ranking at scale at Booking.com
Themis Mavridis, Soraya Hausl, Andrew Mende, Roberto Pagano- ComplexRec @ RecSys ‘20 - Recommending Accommodation Filters with Online Learning
Lucas Bernardi, Pablo Estevez, Matias Eidis, EQbal Osama- ORSUM @ RecSys ‘20 - Personalization in Practice: Methods and Applications
Dima Goldenberg, Kostia Kofman, Javier Albert, Sarai Mizrachi, Adam Horowitz, Irene Teinemaa- WSDM ‘21 - Booking.com Multi-Destination Trips Dataset
Dima Goldenberg, Pavel Levin, — SIGIR ‘21 - Uplift Modeling: From Causal Inference to Personalization
Irene Teinemaa, Javier Albert, Dima Goldenberg- WWW ‘21