A team of industry professionals and Purdue graduate students won the Big Data for Social Good Challenge, a national competition sponsored by IBM.
The winning team was composed of employees from Indianapolis-based big data company Perscio and student researchers in Purdue’s Discovery Advancements Through Analytics (DATA) laboratory. Their winning app submission was titled Watch Flu Spread, based on influenza data.
“This was a great opportunity to work with a private company, which is valuable to students,” said John Springer, director of the DATA lab and associate professor of computer and information technology. “Also, the information they worked with was tangible, which they really connected with. That’s beneficial for helping them understand the significance of their work.”
The app used a simple model of flu spread based on analyses paired with a regression algorithm which learns over time. After conducting the analyses, the team designed interactive visualizations to communicate the results of the computations. Using IBMs Node red tool and sentiment analysis to analyze tweets, the team created a flu map as a public service that can help prevent the spread of flu by providing advanced disease prediction.
“It’s exciting for students to see what they can do from a predictive standpoint. It also allows us to point out, from a teaching standpoint, that there’s a lot of information out there that pertains to people. We can grapple with the ethics that come from the realization that this data can be public,” Springer said.
Perscio will be donating the $20,000 grand prize to Purdue’s Department of Computer and Information Technology.
Read the Perscio blog post announcing the results of the contest.