Barrie Kersbergen is a data scientist with over a decade of experience in the e-commerce industry, specializing in the development of scalable recommendation systems. Since joining bol in 2010, he has played a pivotal role in enhancing customer experiences through recommendation features such as ‘others also viewed’, ‘often bought together’, and ‘search ranking’. His work serve millions of customers daily, driving both engagement and sales.

In 2021, he expanded his expertise by embarking on a PhD at the University of Amsterdam within the “AI for Retail Lab”, under the supervision of Professor Maarten de Rijke and Professor Sebastian Schelter. His research focuses on improving session-based recommendation systems for e-commerce platforms by tackling challenges in predictive performance, latency, and cost-efficient deployment. It presents innovative algorithmic and system-level advancements, including Serenade, a low-latency recommendation system using the VMIS-kNN algorithm, and ETUDE, a benchmarking framework for assessing neural network models. These contributions are rigorously tested using real world datasets, providing significant improvements in performance and operational efficiency in e-commerce environments.