Abstract: The face of retail is continuously changing with consumers seamlessly navigating through multiple channels, and even competitors, to make purchases. Together with consumers steady preference for shorter fulfillment windows, it puts a considerable strain on retailers’ profit margins. Retailers could benefit by reconsidering the traditional approaches to pricing and inventory management siloed by channel and location in this omnichannel era. I will focus on two specific problems: (1) price optimization problem for short-lifecycle items and (2) supply position optimization. For both these problems, I will describe the challenges faced by retailers in the omnichannel context, the problem formulations and the solution strategies that take an integrated approach. I will then discuss experimental results to show the benefits of integration over siloed approaches.
Biography: Pavithra Harsha is a Principal Research Staff Member in the AI Applications division at the IBM T. J Watson Research Center in Yorktown Heights from 2011. She is also a visiting scientist at the MIT Sloan School of Management. Her current research interests are at the intersection machine learning, optimization, decision making under uncertainty with applications to problems in supply chains, pricing, and revenue management. Pavithra received a Ph.D. in Operations Research from the Operations Research Center (ORC) at MIT in 2008. Prior to joining IBM, she worked at Oracle Retail and was a Post-doctoral Associate at the Laboratory of Information and Decision Systems (LIDS) at MIT. She is the recipient of many INFORMS awards including the Aviation Application Dissertation Prize, the Transportation Science and Logistics Dissertation Prize, Services Science Best Cluster Paper award, Revenue Management Practice Award and M&SOM practice-based research Award and IBM awards including the IBM Outstanding Technical Achievement Award and the Outstanding Innovation Award. She has also contributed to commercially used pricing solutions used by top retailers.