Organizations can learn more from internet-connected devices

By Kevin Manne

BUFFALO, N.Y. —  In today’s world of big data, learning from the vast amount of information collected every day is critical for the firms that rely on it for manufacturing, marketing, decision making and more. 

Often, data collected from Internet of Things (IoT) machines on an assembly line or from an app on a shopper’s cell phone is sent to a remote computer in the cloud for analysis and storage—but what if the network connection fails? A new algorithm developed by a University at Buffalo School of Management researcher and recently published in Management Science solves that and other big data problems, all while doing it faster than ever before. 

“Designing algorithms that can learn from data is crucial for businesses,” says the study’s author Haimonti Dutta, PhD, assistant professor of management science and systems in the UB School of Management. “Our model allows devices to communicate with one another—making them robust against network failures—while enhancing the quality of information for decision makers and doing it several orders of magnitude faster than other similar solutions.”

Dutta conducted extensive computational studies using seven publicly available real-world data sets to validate the performance of the model, and found her results were 1.5 times faster than other similar algorithms. She also used it to predict mechanical failures at a chocolate manufacturing plant using more than a million points of data. 

“This case study showed that organizations can use internet-connected devices for much more than collecting data,” says Dutta. “Our algorithm can be used in devices where speed is critical for real-time prediction and learning, like early identification of anomalies that can lead to defects, and applying strategies that allow the devices to adapt and optimize themselves.”