A decade ago the United Postal Service officially introduced their no left hand turns policy. UPS learned through time studies that avoiding left hand turns saves time, conserves fuel, lowers emissions and increases safety. UPS managers combined personal and historical experience with computer programs to design delivery routes, eliminating left-hand turns in hopes of creating increased efficiency. They designed routes in a series of right handed loops with as few left turns as possible.
Since the deployment of this route planning technology in 2004, UPS has eliminated millions of miles off delivery routes creating razor edge efficiency and increased driver’s safety records. A 2004 UPS press release announced a savings of over 10 million gallons of gas and a reduction of over 100,000 metric tons of CO2 emissions after the first year of their no (limited) left hand turn policy.
Fast forward 10 years and UPS has an entire department dealing with using big data that is being captured and downloaded from over 50,000 UPS big brown delivery trucks at the end of each day. Big data enables immediate access to a rear view mirror of what is happening. Business improvement is driven by how the data is used to improve their bottom line.
When structured appropriately, this knowledge can provide competitive advantages over rival organizations. Additionally it can enhance business and employee benefits, structured marketing and profitability. Amazon.com and UPS are two high profile companies using big data to help increase their growth and profitability.
From the office equipment dealer’s service department’s point of view, travel consumes a substantial portion of most field techs’ daily labor hours. The cost of travel is an ongoing burden to the service department’s profitability. The sales reps (with management’s approval) often stretch the territorial boundaries of where equipment is sold. Emergency service calls constantly require the juggling of preplanned service routing.
Many managers do not have the time, commitment or expertise to maximize the value of available data. The best collection of big data is of little practical business value if appropriate monitoring, analysis and follow-through are not utilized.
The UPS big brown local delivery truck is the poster child of increasing productivity by utilizing the information from big data. The UPS Package Flow Technology suite of systems is the catalyst for their process redesign and changes. These systems ultimately synchronize the flow of data throughout UPS, allowing the seamless movement of goods, funds and information.
These changes have eliminated over 85,000,000 miles driven per year. 95% less time is spent on training. 8,000,000 gallons less fuel was used in 2013. 85,000 fewer metric tons of CO2 were expelled by UPS delivery trucks. Implementing analytics technology for UPS drivers required updating every procedure, which is now detailed in the 74 page UPS Driver’s Manual.
Jack Levis, UPS’s Director of Process Management, explains the basics. “We use advanced analytics to reengineer current processes in an effort to streamline the business and maximize productivity. Precise location information is an essential input for improved logistics decision making. This data, along with process analysis and analytical models, have allowed UPS to improve its performance.”
UPS has gone through a long evolution in moving up this analytical hierarchy which required organizational commitment and significant process change. While many lessons were learned along the way, the end result has been reduced cost, improved service to customers, and a data driven architecture for the future.
Working with Big Data normally takes the general forms of:
- Analysis of historical data.
- Prediction of probabilities of future trends
- Evaluation of new ways to operate.
UPS has built a culture of engineering and quantitative analysis. Organizations focus on first gathering their data together and putting them in order, gaining insight from them and making predictions with them. UPS has become a highly creative and profitable technology company that happens to deliver packages.
Analytics come in three categories:
- Descriptive – where we are
- Predictive – where we will be
- Prescriptive – what we should do
Jack Levis wants UPS to go beyond prescriptive analytics by creating clairvoyance. The ultimate goal is to know what problems will occur and to stop them before they happen.
The success of most businesses can be reduced to mathematical probability. Some companies have tougher equations to solve than others. UPS is dealing with approximately 120 daily deliveries made by each of their 55,000 trucks.
Until recently, UPS used a software tool that gave drivers a general route to follow but allowed wide latitude for human judgment along the way. Over the next five years UPS will roll out a more exacting algorithm designed to steer drivers away from well-worn paths toward often counter-intuitive routes calculated to make deliveries faster.
UPS uses On-Road Integrated Optimization and Navigation, aka ORION, to help establish a data-drenched route optimization. The size of the numbers involved means simple arithmetic is out. ORION depends on heuristics, the field of math and computer science devoted to finding answers that are good enough, and that get better based on past experience.
A few of the considerations ORION calculates include finding the shortest distance, promised delivery times, different types of customers and the types of packages being delivered and picked up, in addition to no left turns. Levis is quick to emphasize that UPS doesn’t discount the value of driver wisdom accumulated during years on a route. The best system, he says, is one that relies on both human and algorithmic intelligence.
ORION has proven that if each UPS truck is driven 1 less mile each day, UPS will save over $30 million a year. Currently UPS makes over 16 million deliveries daily. Over 200 million addresses are mapped by UPS drivers. 100 million minutes of UPS trucks idling time has been eliminated by using onboard sensors that calculate when a truck should be turned off or allowed to idle. Currently there are over 200 points monitored on each delivery truck to anticipate maintenance issues and determine the most efficient ways to operate the vehicles.
Levi shared a couple examples. The data collector team figured out opening the truck door with a key was slowing their drivers down. So drivers were given a push-button key fob that attaches to their belt loop. A computer now figures out the best way to load each truck in the morning, and the best way to deliver packages all day. By using Big Data, the average UPS driver has gone from 90 deliveries a day to 120. The drivers have directly benefited from the changes by being the highest paid in the industry.
“The data has become as important as the package is to us,” Jack Levis explains. “It’s my job to think about small amounts of time and large amounts of money. Saving just one minute, per driver, per day, over the course of a year adds up to $14,000,000 in savings to UPS.”
Any business that deals with employees that work outside of the office understands the potential cost and savings that can be attained with properly managed travel expenses. One minute saved by tech per day may not amount to a $14,000,000 savings to your office technology company. However, monitoring, analyzing and pro-actively responding to travel and labor data is a vital part of the overall management of your field employees.
