UPS's New Machine-Learning App Aims To Reroute Packages Away From Snow and Other Trouble Spots in its Global Network (technologyreview.com) 30
If a snowstorm hits Denver, it can delay thousands of packages that travel through the city before reaching their final destinations on the other side of the country. But if UPS knows a storm is coming, what is the most efficient way to divert all those online orders and holiday gifts around the bad weather? UPS grapples with this question every winter. From a report: To help, UPS recently built an online platform that combines machine learning and advanced analytics. The app -- called Network Planning Tools, or NPT for short -- lets the company's engineers view activity at UPS facilities around the world and route shipments to the ones with the most capacity. They can also see details about the packages in transit, including their weight, volume, and delivery deadlines. While UPS already has a system called ORION that maps out last-mile delivery routes, and a program called EDGE focused on upgrading UPS facilities, NPT gives its engineers a bird's-eye view of package volume and distribution across all its pickup and delivery operations.
The app gets some of its smarts from AI, which it uses to create forecasts about package volume and weight based on analysis of historical data. Rob Papetti, who leads NPT development for UPS, says the machine-learning algorithms also analyze decisions the company's engineers made and assess how they affected customer satisfaction and internal costs. "[The app] starts to learn from itself and suggest this option versus that option, based on what enabled us to give our customers better service," he says.
That kind of insight is crucial during the frenetic holiday season. This year, UPS expects to deliver more parcels during that period than ever before --nearly 800 million, up 5% from 2017. In preparation, the company has used the NPT app to identify and eliminate bottlenecks, such as an Illinois facility that was struggling to process packages quickly. "Within a few minutes, we were able to determine how to get around and relieve [the backlog in] that building and still make our service commitments to customers," says Papetti. "Before NPT, that would have taken at least a week." UPS expects the program to save it $100 million to $200 million a year.
The app gets some of its smarts from AI, which it uses to create forecasts about package volume and weight based on analysis of historical data. Rob Papetti, who leads NPT development for UPS, says the machine-learning algorithms also analyze decisions the company's engineers made and assess how they affected customer satisfaction and internal costs. "[The app] starts to learn from itself and suggest this option versus that option, based on what enabled us to give our customers better service," he says.
That kind of insight is crucial during the frenetic holiday season. This year, UPS expects to deliver more parcels during that period than ever before --nearly 800 million, up 5% from 2017. In preparation, the company has used the NPT app to identify and eliminate bottlenecks, such as an Illinois facility that was struggling to process packages quickly. "Within a few minutes, we were able to determine how to get around and relieve [the backlog in] that building and still make our service commitments to customers," says Papetti. "Before NPT, that would have taken at least a week." UPS expects the program to save it $100 million to $200 million a year.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Yes, but that doesn't synergize the deep learning network pipeline with leveraging personalized actionable analytics.
But Where's The AI? (Score:4, Insightful)
In real terms, how is this different then just using historical data and sensors to make rules to route around bottlenecks as they are developing? Yes, this is overall good for the company but it looks like Buzzword Bingo Bullshit to temporarily goose the stock a few points on Wall St. All that's missing is a reference to blockchain. This is not AI or even ML, just basic analytical monitoring and historical reporting.
Re: (Score:2)
Have they figured out the important stuff? (Score:2, Interesting)
If only (Score:2)
They could apply the same algorithm to route the expensive, fragile packages around their employee(s) who seem to delight in doing everything in their power to destroy them :|
The primary reason I don't order $$$ items from an online retailer is due to the 50 / 50 chance of it arriving undamaged.
Relevance (Score:2)
The most relevant tweet ever made about AI is still just as relevant today: https://twitter.com/iamdevlope... [twitter.com]
Meanwhile... USPS is still confused (Score:2)
I had a package shipped from S. California to me in N. California. It spent 2 weeks in City of Industry USPS sorting facility waiting for "acceptance". They tell me it might be delivered by Friday if I'm lucky.
No snow yet this year but there will be snow by Friday so I think they were waiting for snow to deliver it so they could do their "Neither rain nor snow... etc." thing.
How about ... (Score:2)
Re: (Score:2)
New England doesn't need a hub
Nobody is going to use New England as a hub for anything. It's either a start or end point for shipping. And if the weather there goes to hell, there is no way to route around it. Your mail/packages will just have to wait. Unless your alternative is to load them on dog sleds.
Small amendement (Score:2)
"Neither snow nor rain nor heat nor gloom of night stays these couriers from the swift completion of their appointed rounds" ...unless AI told us so.
They are slow to implement routing concepts (Score:2)
Going back several decades, network protocols such as OSPF were designed as a way for networks to automatically reroute around problems and to allow for manually adjusting for things like congestion on a network to route around problems. It should NOT have taken this long for a company like UPS to come up with something similar to route around problem areas when it comes to traffic. People with a computer science degree should have been brought in back in the 1990s to come up with a good package routing
This will be popular in Canada (Score:2)
Oh.
Wait.
Hmm, maybe not.