Software at Your Service
Every day, businesses with large service fleets brace for the unpredictable. How many calls for service will stream in during the day? Where will the nearest technicians be, and will they have the right parts in their repair kits? For companies handling hundreds, even thousands, of calls a day, coordinating service is immensely complex-and wrong answers can be immensely costly.
Now, researchers at IBM are unveiling software that will answer all those questions automatically. The IBM algorithms continually account for data-ranging from which customers have called for service to whether a technician’s van has broken down-and periodically churn out instructions representing the best way to deploy the work force at that moment. “I think our approach of continually reoptimizing every 10 to 15 minutes is basically unique to us,” says Baruch Schieber, a computer scientist at IBM Research in Yorktown Heights, NY. What’s more, he adds, the IBM system relies less on previous calculations when performing new optimizations than other approaches do, so errors don’t snowball over time.
Features like this make the IBM tools innovative-and give them unprecedented breadth and power, says David B. Shmoys, a computer scientist at Cornell University. “They’re leveraging state-of-the-art theoretical ideas and bringing them to bear on practical problems in an interesting way,” Shmoys says. Plus, the IBM approach juggles seven factors, from customer locations to parts availability-a feat that Schieber says is unique in a field where five and six are considered difficult.
IBM started using earlier versions of its algorithms in its own 6,000-employee service unit in 1998 but landed its first customer this year. An IBM commercial product is a sign that the market for service optimization software is booming, says Moshe BenBassat, chairman and CEO of one firm in that business, Campbell, CA-based ClickSoftware. Many companies have already optimized manufacturing, but optimizing service delivery “is a much harder problem” because of unpredictability, he says.
IBM’s software aims to tackle such hard problems, so that the unpredictable doesn’t have to be unmanageable.
Keep Reading
Most Popular
Large language models can do jaw-dropping things. But nobody knows exactly why.
And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.
The problem with plug-in hybrids? Their drivers.
Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.
How scientists traced a mysterious covid case back to six toilets
When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.
Google DeepMind’s new generative model makes Super Mario–like games from scratch
Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.
Stay connected
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.