Who is Going to Get the Flu Next?

The IBM Challenge

IBM challenged developers from around the world to use their skills to do something good for the world. The challenge invited developers to use their curiosity and talents to dive into a real world civic issue by analyzing a dataset with Bluemix and creating a clickable interactive visualization that reveals meaningful insights. The Challenge was originally posted in November, and Flu season was imminent. Since as many as 20% of Americans are affected by the Flu each year, finding a way to track the spread of the virus and provide real time information about its likely path of spreading would be invaluable to the public.

Enter Perscio

Perscio teamed up with a group of graduate students from Purdue's D.A.T.A. Laboratory to develop the Watch Flu Spread app for the challenge. The app uses  a simple model of flu spread based on analyses, paired with a regression algorithm which learns over time, and incorporates an interactive visualization to communicate the results of the computations. Using IBM Bluemix tools like Node red 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.

View Our Official Entry

Grand Prize Winner

Perscio and Purdue won Grand Prize among 1,300 participants globally!

The Solution

The thrust of the challenge is IBM's invitation to developers like us to use our curiosity and talents to dive into a real world civic issue by analyzing a dataset with Bluemix and creating a clickable interactive visualiziation that reveals meaningful insights. This is what we at Perscio do - so we were excited to jump right in!

Our submission, Watch Flu Spread,  takes a deep dive into Influenza data. Since as many as 20% of Americans are affected by the Flu each year, we felt that finding a way to track the spread of the virus and provide real time information about its likely path of spreading would be invaluable to the public. Our app uses a simple model of flu spread based on our team (which included Purdue students) analyses, paired with a regression algorithm which learns over time. We used interactive visualization to communicate the results of the computations.

Challenges such as this fuel us at Perscio. Nothing like building a live, learning system out of multiple data streams from multiple sources to get our lab fired up. Let us put these technologies to work for you so that you can begin leveraging the power of your own data - and the world of open data!

Perscio is honored to receive a personal congratulations from Mitch Daniels, president of Purdue University and former Governor of Indiana.

Challenges such as this fuel us at Perscio. Nothing like building a live, learning system out of multiple data streams from multiple sources to get our lab fired up. Let us put these technologies to work for you so that you can begin leveraging the power of your own data - and the world of open data!