Prescriptive Analytics Project Delivering Big Dividends at UPS

by   |   April 19, 2016 5:30 am   |   0 Comments

Thomas Davenport

Thomas Davenport

I recently attended the 2016 INFORMS Conference on Business Analytics and Operations Research in Orlando. INFORMS, the Institute for Operations Research and the Management Sciences, has historically had an Operations Research –  that is, optimization of logistics and resources – focus, but the organization is slowly branching out into other areas of analytics.

A hallmark of this annual conference is the awarding of the Franz Edelman Award, which recognizes excellence in Operations Research and analytics in the public and private sectors that changes the involved organizations. I suspect that most readers have never heard of either Franz Edelman (who headed Operations Research at the no-longer-with-us RCA Corporation) or the award, but the Operations Research community takes it very seriously. I am somewhat marginal to the Operations Research gang – I view it as just another type of analytics, but the winners often set a great example for the rest of the world.

That’s particularly true this year, when the winner was logistics and parcel delivery company UPS, for its ORION project. ORION, an acronym that stands for On-Road Integrated Optimization and Navigation, is perhaps the largest commercial analytics project ever undertaken. It’s required well over a decade to build and roll out, and more than $250 million of investment by UPS. At its peak, over 700 UPSers were working on change management and rollout of the system. So the company clearly went all in on this project.

Because they won the award, you might guess that the company is receiving something in return for its investment; and indeed it is. How about savings (in driver productivity and fuel economy) of between $300 and $400 million a year? How about 100 million fewer miles driven and a resulting cut in carbon emissions of 100,000 metric tons a year? You don’t see those levels of benefit from an analytics project very often, and these have been confirmed through intensive measurement and reported to Wall Street analysts.

Related Stories

Predictive Analytics Driving Results, ROI at UPS.
Read the story »

Location and Insight in the Age of the Internet of Things.
Read the story »

Predictive Analytics Captures Value in Every Business Sector.
Read the story »

The Role of the Shipping Parcel in a Data Management Strategy.
Read the story »

What does ORION do? It’s basically prescriptive analytics for UPS’ 55,000 drivers in the United States (the international rollouts will come soon). Instead of following the same route every day, ORION analyzes the packages to be delivered that day and determines an optimal routing for the “package cars.” The drivers are told where to go next by their handheld computers.

You also may be wondering why ORION was so expensive and took so long to roll out. There are two fundamental reasons: maps and change management. The optimization algorithm itself was difficult to develop, but that aspect of the work paled in comparison to the other two components. UPS had to develop its own maps to ensure that the drivers would be directed to the right place every time, and to the correct location for package drop-off or pickup. No commercially available maps could do that for the 250 million different locations to which UPS delivers.

Secondly, imagine that you have to communicate and inculcate a new way of performing a core daily task to 55,000 workers. UPS devoted six days of training and support to each of the drivers. To their credit, most of the drivers wanted to know how the system worked before they would give up their time-honored routes, and so considerable effort was devoted to turning the “black box” algorithm into a “glass box.” Most of the drivers were enthusiastic about the new approach once they had experienced it.

Jack Levis, the company’s Senior Director of Process Management who also leads the Operations Research and Advanced Analytics groups, led the ORION project and cites six factors as the reasons for ORION’s success:

    • Education. Education about the system took place at every level, from CEO to drivers


    • Communication of the vision. Lots of effort went into explaining how the system would work and how it would add value.


    • Support from the top. As an indication of this, UPS’s CEO, David Abney, a former driver himself, was present at the INFORMS conference and testified to ORION’s value.


    • Quick wins. ORION really involved a series of smaller projects, each of which brought benefits.


    • Training and certification. These were a major component of the staffing and expense of the project, but absolutely necessary.


    • Measurement. The project maintained a dashboard down to the local district level about how the rollout was proceeding and the benefits achieved from adoption.


Of course, it didn’t hurt that UPS has a long history of measurement and improvement through industrial engineering. Many companies would have had to change their cultures in this direction before taking on a project like ORION, but UPS already had it.

And the benefits from ORION are only just the beginning of what UPS can realize. There is, of course, the global rollout of these tools. And to maintain a level of simplicity for drivers, ORION only optimizes routes at the beginning of the workday. More sophisticated programs down the road could re-optimize during the day, take traffic patterns into account, and even get one driver to exchange packages with another during their routes.

There aren’t many companies that have made bets on analytics to this degree. When I first began writing about them a decade ago, I referred to such companies as “analytical competitors.” When you invest in analytics at the level of hundreds of millions of dollars – and more importantly, deliver value at multiples of that sum – it’s safe to assume that you are competing on analytics.

Tom Davenport, the author of several best-selling management books on analytics and big data, is the President’s Distinguished Professor of Information Technology and Management at Babson College, a Fellow of the MIT Initiative on the Digital Economy, co-founder of the International Institute for Analytics, and an independent senior adviser to Deloitte Analytics. He also is a member of the Data Informed Board of Advisers.

Subscribe to Data Informed for the latest information and news on big data and analytics for the enterprise.

Tags: , , ,

Post a Comment

Your email is never published nor shared. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>