Dr. Kevin Kahn is the co-founder and CEO of Albatross, a Switzerland-based artificial intelligence company pioneering perception models. Today, Albatross is orchestrating 100+ million products, processing tens of billions requests per year, and has raised $16 million from leading investors MMC Ventures, Redalpine, and Daphni.
Prior to Albatross, Kevin led machine learning and recommendation platforms at Amazon Music. He was also head of business development at a semiconductor startup acquired by Asahi Kasei, and a research fellow at the National University of Singapore. Kevin holds a PhD in applied physics from Imperial College London and an MBA from the University of Chicago Booth School of Business.
Product Discovery for Marketplaces is Finally Solved: Introducing Perception Models
Second-hand marketplaces have a discovery problem that traditional recommendation systems were not built to solve: every item is unique, catalogs change rapidly, and metadata is inconsistent. Hundreds of thousands of new listings enter the catalog every day with no impressions or interaction history - effectively invisible to legacy systems. The result is a discovery experience that remains static as users browse, click, and refine their interests, while newly listed items can take days to surface.
Albatross has solved this problem with a new class of AI: perception models. These models learn from live user behavior, understand user intent in real time, and reshape discovery as each session unfolds - while every new unique item becomes immediately discoverable.
In this talk, we will show how perception models work, and explore their impact for the future of marketplaces. Drawing from live deployments with leading marketplaces, we will share how Albatross has delivered more than 2x lift in engagement and tens of millions of incremental GMV; proof that discovery for recommerce is no longer an open problem.
