Skip to Content
MIT Technology Review

How machine learning is accelerating last-mile, and last-meter, delivery

Wise Systems’ routing software helped one company cut late deliveries by 85%.

March 25, 2019

While much of the logistics industry’s efforts to accelerate delivery times focuses on optimizing routes, it turns out that’s not where drivers spend most of their time.

In fact, as much as 75% of their workday is dedicated to navigating not the “last mile” but the last 100 meters—waiting at loading docks, searching for parking, and interacting with customers, said Chazz Sims, chief executive of Wise Systems, a startup based in Cambridge, Massachusetts, that has developed autonomous routing and dispatch software.

Using data and machine-learning tools, the company found that this kind of service time varies widely depending on the time of day, the specific customer, the goods in question, and the delivery person, Sims added. For instance, certain shops get busy serving customers at particular times of the day, or receiving goods from different delivery trucks at others. By spotting those patterns and shifting schedules around, the company was able to cut down delivery times and costs.

Wise Systems’ tools automatically adjust routes, drivers, and schedules throughout the day in response to other shifting conditions as well, including weather, traffic, and backed-up loading docks. By analyzing data from the fleet of brewing company Anheuser-Busch, one of the startup’s biggest customers, Wise Systems was able to cut late deliveries by 85% and fleet miles by 13%.

The business, founded in 2014, raised $7 million from Google’s AI fund late last year.