Talk Abstract: It takes a huge industrial machinery for people to order and receive their Amazon packages. The warehouses and trucks are visible, but the billions of decision made every day and the algorithms that make them are not. As we follow the journey of an Amazon package, we outline the types of decision problems that are solved in Amazon Supply Chain Optimization Technologies (SCOT), and point out academic work used to solve them. We dive in some detail into published aspects of assortment optimization algorithms, and describe the engineering challenges our scale brings. We discuss the depth of science work at Amazon, the scale of its science and engineering communities, and opportunities work to with and/or for Amazon to advance technology on behalf of our customers.
Location: 2:00-3:00 p.m. on Friday, March 25th on Zoom (password: CS2022) Virtual attendees must be signed into Zoom with their university account or chose "Sign in with SSO" to attend this meeting.
Note: CS2003 students attending in person in Sennott Square room 5317 must sign in and out of the event.
Biosketch: Tomas Singliar, University of Pittsburgh CS PhD class of 2008, is a business quantitative scientist with experience in forecasting, inventory, pricing and profitability. Today he is working in Amazon on measuring substitution between items, and designing supply chain optimizations using cross-item relations. Tomas received four patents in inverse reinforcement learning held by Boeing, built AI-in-the-cloud solutions for consulting customers and led the development of a Python forecasting SDK at Microsoft. He has published in, organized and served on program committees of ICML, KDD, AAAI, as well as similar internal venues at Amazon and Microsoft. He can also help with econometrics, big data compute performance and key business metric formulation.
Host: Daniel Mosse