Aleksandr V. Petrov

I am a Research Scientist at Spotify, where I focus on making generative language models work effectively for search and recommendation tasks. I recently completed my PhD in Machine Learning at the University of Glasgow (awarded with distinction), supervised by Prof. Craig Macdonald and Prof. Iadh Ounis. My doctoral research on transformer models for sequential recommendation was recognised with the Best Paper Award at RecSys 2023 and a nomination at RecSys 2022.

Prior to Spotify, I was a Senior Scientist at Tripadvisor (Viator), where I deployed production semantic search models, and an Applied Scientist at Amazon, where I led large-scale ML projects for advertising and personalisation. I also co-founded E-Contenta, a startup providing white-label recommender systems for media platforms.

My research is published in top-tier venues including SIGIR, RecSys, WSDM, and ECIR, as well as ACM Transactions on Recommender Systems (TORS). I actively serve the research community as a PC member for RecSys, WWW, and ECIR, and as a reviewer for journals such as TOIS and TKDD.

In my free time, I enjoy driving through the Scottish Highlands, studying languages, and reading fantasy books.

Get in touch: firexel@gmail.com