Machine Learning at Amazon

Jason Murray, VICE PRESIDENT OF WORLD-WIDE RETAIL SYSTEMS, AMAZONAt the November 2016 meeting of the Operations Research Society - INFORMS - Jason Murray, Vice President of World-wide Retail Systems at Amazon gave a very informative talk about how Amazon uses machine learning throughout its online retail operations. 

For example, Amazon uses automated machine learning models to negotiate with its numerous medium and small-sized suppliers. His slides, photographed by a participant, provide a rare glimpse into the machine learning ways of Amazon.  While the algorithms are not spelled out in detail, it is unusual for a big tech company like Amazon to offer the analytic community a review like this. If you'd like to see the presentation yourself, click here.


Title: Optimizing the Future – Supply Chain at Amazon

Abstract: The retail supply chain of the future will be built on massive data, advanced analytics and innovative technology. At Amazon, we are constantly pushing the frontier in each of these areas to help create that future. Our vision is to move products at an unprecedented scale through the most technologically advanced supply chain possible, where intelligent optimization algorithms drive efficiency. To achieve this vision, we focus on three core pillars: research, technology, and business ownership. We develop new research, implement it in technology, and own the top- and bottom-line of the business. To be successful, we believe business ownership, research, and development must be tightly coupled.

During this presentation, I will discuss our vision for the future of retail supply chain — where we have been, where we are, and where we plan to go. I will share some cases of research innovation and its integration with technology and business. These include inter-disciplinary modeling and optimization (from machine learning, statistics, simulation and optimization) to make Amazon’s supply chain more efficient. Finally, I will provide examples of some challenges we will need to overcome to make our vision a reality.

Bio: Jason joined Amazon in 1999 as a Software Development Engineer in Fulfillment Center (FC) Systems and moved to a Development Manager role in 2003.  In 2007, he joined Fulfilled by Amazon (FBA).  He took over Inventory Planning & Control (IPC) in 2009, and was promoted to Director in 2010.  Under his leadership, the IPC team grew to over 300 employees worldwide.  IPC is responsible for Economically Optimal Ordering, Sourcing Cost Optimization, Optimal Inventory Health, Vendor Returns, EDI, Inventory Flow Simulation and Inbound Performance Management.

In 2013, he was promoted to Vice President of Supply Chain Optimization Technologies (SCOT) were he led 700 global employees in the areas of Forecasting, Inventory Planning, Optimal Sourcing, FC Topology planning and Customer Promise.  The platform is responsible for the automated buying, markdown, order assignment and placement of inventory in our fulfillment network. SCOT is also responsible determining customer delivery promise and planning the topology and capacity of our fulfillment network.

In 2016, he was appointed the Vice President of World-wide Retail Systems.  Jason runs a world-wide organization consisting of approximately 6000 global employees. Retail Systems helps product lines grow profitably by providing automation and workflows for increasing selection, matching relevant competitors on value, and getting the best terms from vendors. The team also works with subsidiaries to deliver the services, integration support, and solutions design to migrate onto the Amazon platform. Retail Services provides the operational and creative resources behind product imaging, new item setup, competitive monitoring and various flex tasks.

Jason holds a Computer Science degree in Engineering from the University of Washington.  He is an avid runner and practitioner of Brazilian jiu-jitsu.  He lives in Bellevue, Washington with his wife and 3 children.

Want to be notified of future courses?

Student comments