In this talk, we describe the data science framework at Udemy, which currently supports the recommender and search system. We explain the motivations behind the framework and review the approach, which allows multiple individual data scientists to all become 'full stack', taking control of their own destinies from the exploration and research phase, through algorithm development, experiment setup, and deep experiment analytics. We describe algorithms tested and deployed in 2015, as well as some key insights obtained from experiments leading to the launch of the new recommender system at Udemy. Finally, we outline the current areas of research, which include search, personalization, and algorithmic topic generation.
Data Science at Udemy: Agile Experimentation with Algorithms
Larry Wai is an avid scientist who’s currently the principal data scientist at Udemy, a global marketplace for learning and teaching, where he’s pushing the frontiers of education technology. Larry has designed a unique scalable framework that allows multiple individual data scientists to become “full stack,” taking control of their own destinies from the exploration and research phase, through algorithm deployment, experiment set-up, and deep analytics. Prior to joining Udemy, Larry was a lead data scientist at Groupon and, earlier, a principal analyst at Yahoo Search. He has published and pending patents related to search and discovery data science methods. Before moving into the consumer Internet field, he was a scientist working on particle astrophysics, with physics experiments ranging from neutrino oscillations to detection of dark matter. He was recently awarded a portion of the 2016 Breakthrough Prize in Fundamental Physics for fundamental discovery and exploration of neutrino oscillations.