Professor uses student ID card data to help predict dropouts
Apr. 01, 2018
PHOENIX (AP) — University ID cards could yield ideas on how to help lower college dropout rates, according to a University of Arizona professor who is digging into years of data on cardholders' shopping habits, social circles and other characteristics.
Sudha Ram, a professor of management information systems at the Tucson university, believes her preliminary study may have found a better way to predict which freshmen will likely drop out, The Arizona Republic reported .
Student IDs, called CatCards, are used at about 700 campus locations, including residence halls, the recreation center and the library. Ram worked with university Information Technology to gather and analyze data on the use of freshmen's IDs over a three-year period, according to the university.
The preliminary study showed social integration and routine were better predictors of freshman retention than end-of-term grades — a marker traditionally used to gauge retention.
"We live in an era where you shouldn't be generalizing about groups of people," Ram said. "You should be personalizing solutions at the individual level."
The study has raised privacy issues, even though the researchers did not receive students' names, ID numbers or any other information that could lead to their identities, according to the university.
The university has not put Ram's research into practice, a university spokesman said.
The University of Arizona increased the freshman retention rate to 83.3 percent in 2017 from 80.5 percent in 2016 but hopes to improve the number even further.
Before starting the study, Ram submitted her plan to the Institutional Review Board, which is an independent review committee that works to protect human research subjects.
The board determined the study would not harm students and protect their privacy, according to a university spokesperson.
Albert Gidari, director of privacy at Stanford Law School's Center for Internet & Society, believes the University of Arizona could run into several issues if deciding to pursue the project, including reaction from freshmen whose actions would be monitored.
Schools like Georgia State University already use data to track at-risk behaviors to help advisers intervene. Georgia State has been able to improve graduate rates and decrease the achievement gap between racial and ethnic groups, according to the university.
The University of Arizona uses around 800 data points, such as academic performance and financial aid, to help determine which students are at risk to drop out.
The accuracy rate is around 73 percent from the first day of class, and is improving over time, University of Arizona Assistant Provost for Institutional Research Angela Baldasare said.
"The kind of move that universities are making toward predictive analytics and using more data to understand the student experience allows us to look earlier and more often at some of the variables that we can get our hands on, and ask different sorts of questions than we are able to ask before about the freshman experience," said Vincent J. Del Casino Jr., University of Arizona vice president of academic initiatives and student success.
Information from: The Arizona Republic, http://www.azcentral.com