Data science at Udemy: Agile experimentation with algorithms

The data science system at Udemy
¹
, a global online education marketplace, is described. This data science system currently supports recommendation and search, but will be extended to support e-learning as well. The motivations behind and the approach to the system are explained, 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. Algorithms tested and deployed in 2015 are described, as well as some key insights obtained from experiments leading to the launch of the new recommender system at Udemy. Finally, current areas of research in applied computing are outlined, which include search, personalization, and algorithmic topic generation.