An algorithm designed to spot struggling students and offer guidance and assistance even in the first couple weeks of their college career proved highly effective at Purdue University over the past six years.
The program, known as Signals, is one of the first advanced analytics programs to identify at-risk students by delving into reams of data that offer a clear picture into how a student in adjusting to her college education.
Signals examines numbers gathered from more than 20 data points stemming from learning management systems used at Purdue.
Purdue students enrolled in at least two courses that used the Signals program graduated within six years at a 21.5 percent rate higher than students who didn’t take classes that used Signals, according to statistics released by the university.
Campus technologists have long pushed for widespread adoption of analytics that could improve retention rates, emphasizing that technology could serve as a central piece of a larger effort to keep students in school, on a path toward graduation.
“Academic analytics can help shape the future of higher education, just as evolving technology will enable new approaches to teaching and learning,” Kimberly Arnold, educational assessment specialist for Purdue’s Teaching and Learning Technologies group, wrote.
Arnold added that beyond applying analytics programs like Signals, “effective teachers will continue to interact with their students; students will continue to work cooperatively and be accountable for their own education; feedback will continue to be important.”
Based on the data compiled by Signals, the solution displays a red, yellow, or green signal to students and faculty, indicating a student’s achievement status in a course in real time.
A red light indicates a high likelihood of failing; yellow indicates a potential problem of succeeding; and green signals a high likelihood of student achievement.
Students view the signal within the institution’s learning management system and also receive it via eMail. Along with the signal, students receive suggested resources and recommended courses of action from faculty as needed.
John Campbell, associate vice president for academic technologies at Purdue, said Signals can catch struggling students as early as two weeks into the start of their college education.
“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. This very early alert to the student is extremely valuable, even in populations where you might not think it is necessary,” Campbell said.
- Research: Social media has negative impact on academic performance - April 2, 2020
- Number 1: Social media has negative impact on academic performance - December 31, 2014
- 6 reasons campus networks must change - September 30, 2014