Back

Speaker "Suman Bhattacharya" Details Back

 

Topic

When AI Meet Experimentation
 

Abstract

At Uber we have built experimentation platform to enable conducting experiments at scale. Most experiments are performed under A/ B testing setting. I will discuss standard technique used and potentials pitfalls to avoid during hypothesis testing. Because of the nature of a global market place, sometimes experiments are conducted in a non A/B fashion using Synthetic Control technique. Applications of artificial intelligence (AI) is used in practically every industry domain. A relatively new area of application of AI is hypothesis testing through experimentation. I will discuss how Uber leverages AI to build technique for conducting non A/B experiments.

While doing experiments, guarding against potential regressions on business metrics is just as important as conducting the experiments. I will discuss deep learning based techniques that are used to detect regressions in business metrics during the experiments and the feature roll out.

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