Back

Speaker "Suman Bhattacharya" Details Back

 

Topic

Data Science and Fashion

Abstract

In recent years, a new breed of fashion companies have started leveraging data to understand their customer choices. Customer provides feedback which is then used to send clothing that are personalized to customer’s tastes. Since these companies are purely online only, predicting the right size for the garment that will fit the customer, is just as important as recommending right styles. The holistic goal is to present a personalized assortment of clothes that matches customer’s tastes and fit. I will discuss recommender systems in general and how it plays a pivotal role to deliver personalized fashion.

A second aspect to building predictive model is experimentation and improvement of the algorithm using customer feedback. I will discuss how using a technique called Multi Arm Bandit help improve the online accuracy of the recommender system.

Profile

I hold a PhD in Astrophysics and have worked as a numerical astrophysicist in the past applying different machine learning and statistical technique to draw inference from large datasets. After joining Thoughtworks, I started working at Gap Inc. big data team (Thoughtworks engagement). At Gap, I worked on various customer personalization projects like predicting attrition rate, predicting shopping behavior of customers etc. After Gap, I worked at Samsung Research as a staff research engineer on health care analytics and computer vision projects. After Samsung, I worked at LeTote where I built machine learning models to personalize shopping experience for the customers. Currently I work at Uber on various optimization problems