Mercury Machine Learning Lab

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

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

Research projects cover fundamental research topics. These are numerous and include 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 generalisation and domain adaptation; and novel language processing models for better generalisation.

Such topics are of both fundamental scientific importance and immediate practical relevance for modern online businesses such as Booking, which aim to maximise customer satisfaction in quickly changing markets with the help of sophisticated data analytics.