News

Marist College Uses Predictive Analytics to Identify At-Risk Students

By

Marist College in New York is using predictive analytics to address the degree completion crisis trending in higher education across America, school officials announced.

By utilizing Pentaho's open-source Business Analytics Platform, Marist students, faculty and staff were able to engage in the research, development, and implementation of an early alert system, which is able to identify at-risk students.

"As a leader in educational applications of technology, Marist is committed to offering students, faculty, and staff the benefit of advanced open-source technologies," Bill Thirsk, Vice President and CIO at Marist College, said in a statement. "The capability to provide a timely intervention to assist a student that is at risk promotes a strong sense of community between student and teacher, illustrates our commitment to service using technology, and provides a provably excellent learning experience."

The open-source "academic early alert system" predicts which students in specific courses are not likely to complete the course successfully within two weeks of the start of the course.

"Marist's 360 degree view of student performance is one of the most common big data use cases Pentaho addresses in the shifting sands of the big data ecosystem," explains Donna Prlich, Vice President, Product and Solutions Marketing at Pentaho. "By harnessing the power of Pentaho's big data integration and predictive analytics capabilities Marist College has successfully reduced college dropout risks before they happen."

By creating a predictive portable model, Marist was able to successfully deploy the academic early alert system to more than 2,200 students at community colleges and Historically Black Colleges and Universities (HBCUs) around the United States as a means to research the effectiveness of the predictive analytics and intervention strategies. The accuracy of the predictive model when deployed at these partner institutions was in the 75 to 79 percent range.

"Not all open source projects are equal or have the same impact on our student's success. Partnering with Pentaho provided us the big data tools we needed to make a difference in student outcomes, one course and one student at a time," Thirsk added.

© 2024 University Herald, All rights reserved. Do not reproduce without permission.
Join the Discussion
Real Time Analytics