In this talk, I will present an overview of recommender systems, including traditional content
based and collaborative filtering. I will also touch upon some current trends and breakthroughs in
this area. I will then provide an overview of how we develop recommendations here at Etsy.
Specifically, I will provide an overview of our journey from linear ranking models to a non-
linear deep neural network ranking model, the challenges we faced and the lessons we learnt. I
also plan to present our work on a novel custom objective function to build a recommendation
model that jointly optimizes both relevance and profit.
=Senior Data Scientist at Etsy, a two-sided marketplace for buyers and
sellers. At Etsy, Moumita is the tech lead of a team that develops recommendation systems to
show relevant items to Etsy users. Moumita has a PhD in Computer Science
with a focus on Machine Learning and its applications in disease prediction and patient risk
stratification.