Purdue Beta Tests Early Intervention System

• By Dian Schaffhauser
• 10/20/10

Purdue University in West Lafayette, IN and SunGard Higher Education are in the beta testing phase of a jointly developed application that taps into data from course management, student information, and gradebook systems to predict how well a student is performing in a course. Course Signals warns students who are at risk of failure via e-mail and with a traffic signal light that shows up in the CMS. The student also receives suggestions for resources and recommended courses of action from faculty as needed. The goal is to strengthen an institution's retention efforts by helping the student succeed.

Based on the data pulled from multiple sources, Course Signals displays a red, yellow, or green signal to students and faculty, indicating a student's status in a course in real time. A red light indicates a high likelihood of failing a course; yellow indicates potential problems; and green signals a high likelihood of succeeding. According to the developers, the system can make assessments as early as two weeks into a new academic session.

The program is built on a predictive model developed by John Campbell, the associate vice president of academic technologies at Purdue. "The predictive model in Course Signals gives students a good indication very early in the course of how they are performing, and whether they are starting to lag behind others in the class," said Campbell. "This very early alert to the student is extremely valuable, even in populations where you might not think it is necessary." He noted that the program is helping Purdue improve retention rates by identifying underperforming students early on and providing them with course-specific advice on how to change their trajectory."

One beta site for the program is Metropolitan Community College-Kansas City (MCC). "We have a lot of students who are the first in their families to attend college, or who have other demographics that indicate they might be at risk early on," said Tuesday Stanley, vice chancellor of administrative services and student development. "The other solutions we have seen only consider grades when identifying at-risk students. The inclusion of demographics, as well as effort, is a critical piece of the equation in helping these students succeed."

She added that Course Signals streamlines the process for faculty, thereby making it easier for them to reach out to students who need extra support. "Other solutions require faculty to do considerable upfront work to set it up and are cumbersome to execute," Stanley said.

In the initial release, Course Signals will work with SunGardHE's Banner Digital Campus, Oracle's PeopleSoft student information systems, and various Blackboard CMS platforms. Integration with other student and learning management systems is planned.