Mercury Machine Learning Lab

The Mercury Machine Learning Lab is a collaboration between University of Amsterdam, Delft University of Technology and The lab focuses on the development and applications of artificial intelligence to the specific domain of online travel booking and recommendation service systems.

The collaboration of Mercury Machine Learning Lab combines expertise of scientists from the University of Amsterdam (information retrieval, causality and natural language processing), Delft University of Technology (reinforcement learning) with the unique expertise, experience and availability of big data at Booking. Over the period of five years, six PhD researchers and two postdocs work in the lab on six work packages.

The research projects cover fundamental research topics, ranging from model-based exploration, parallel model-based reinforcement learning, methods for combined online and offline evaluation, prediction methods that correct for undesired feedback loops and selection bias, domain generalization and domain adaptation, and novel language processing models for better generalization. These topics are both of fundamental scientific importance, as well as of immediate practical relevance for modern online businesses like Booking that aim to maximize customer satisfaction in quickly changing markets with the help of sophisticated data analytics.

MMLL webinar series

The Mercury Machine Learning Lab (MMLL) organizes the MMLL online seminar series. Each event will last one hour, with a 5-minute intro by one of the lab representatives about the lab and its objectives, 40-minute talk by the keynote speaker, and a 15 minute Q&A session.

Webinar videos

ICAI MMLL webinar I – Mercury Machine Learning Lab webinar 1: Prof Juan D. Correa on Causality
ICAI MMLL webinar IV – From Sparse Modeling to Sparse Communication
ICAI MMLL webinar V – Causality-inspired ML: what can causility do for ML? The domain adaptation case.

A selection of research topics

Model-based Exploration

Effectively performing exploration in the non-stationary and multi-faceted environments that interacts with.

Bridging online and offline evaluation

To develop and evaluate methods, both theoretically and experimentally, that bridge the gap between online evaluation and offline (off-policy) evaluation.

Novel language processing models for better generalization

To develop methods for training NLP models that explicitly target generalization across multiple related tasks.

Scientific Directors

Joris Mooij

Frans Oliehoek

Matthijs Spaan

Onno Zoeter (Industry Director)

Joris Mooij is a Professor in Mathematical Statistics at University of Amsterdam.
Frans Oliehoek an Associate Professor in the Department of Intelligent Systems at Delft University of Technology.
Matthijs Spaan is an Associate Professor in the Department of Software Technology at Delft University of Technology.
Onno Zoeter is a Principal Data Scientist at

Partners has grown from a small Dutch startup in 1996 to one of the world’s leading digital travel companies.
Delft University of Technology is a leading international university that combines science, development, and design.
University of Amsterdam is a modern institution and one of Europe’s most prominent research-led universities.