Kim Falk is a data scientist whose career has focused on machine learning for recommender systems. He has built recommenders for customers including BT and Manning Publishing, and added user segmentation to Sitecore CMS, work that combines the statistical side of recommendations with the practical realities of integrating them into live products.

Kim’s interests stretch beyond recommenders. He has worked on Danish NLP models for named entity extraction and built a deep learning classifier to predict the verdicts of legal cases, projects that show the same pattern: taking a real-world dataset, applying current ML research, and delivering a result that works in production. He has experience leading small teams and stays keen on research, keeping up to date with the field while keeping a firm focus on results.

He is the author of Practical Recommender Systems, a Manning book that walks readers through building recommendation engines from the ground up, from implicit feedback and content-based filtering to neural approaches. The book reflects how Kim teaches and works: pragmatic, example-driven, and always anchored in systems that ship.