ROBERT SIEGEL, HOST:
The same kind of technology that recommends movies on Netflix or purchases on Amazon is now helping students choose college courses. A new program developed on a campus in Tennessee uses predictive analytics to suggest classes. And now the technology is spreading across the country. It's seen as a way to make higher education more efficient.
Blake Farmer, of member station WPLN, reports.
(SOUNDBITE OF CROWD)
BLAKE FARMER, BYLINE: It's the lunch hour at Nashville State Community College. Students snack on chips as they cram for finals. But many may be wasting their time. On average, graduates take nearly a year's worth of classes they could have done without, or they drop courses before making a bad grade. For Jonathan Hudspeth, it was anatomy and physiology.
JONATHAN HUDSPETH: It just wasn't for me. Like, it was the terminology was too big. You had to remember how to spell it. And it just wasn't my area of what I wanted to do.
FARMER: Perhaps it would have been best to navigate around the class altogether. That's what a program, aptly named Degree Compass, is designed to do. Tyler Milton is studying nutrition at Austin Peay State University in Clarksville, Tennessee. She logs on to see a list of courses. Some have five stars beside them, others have one or two.
TYLER MILTON: And if I'm stuck between choosing between intro to philosophy and intro to ethics, I can come here and see that intro to philosophy would probably be a better option for me.
FARMER: It sounds like straightforward advice but the outcomes have turned heads - from the White House to Bill Gates, whose foundation pitched in startup funding.
BILL GATES: The early results at Austin Peay have been promising. Students do half a letter grade better in classes suggested by Degree Compass than in classes they pick the old-fashioned way.
FARMER: And perhaps more importantly, minority and low-income students - who tend to have a harder time finishing a degree - experience an even bigger boost. But how does it know what classes will be a better fit? Mathematician Tristan Denley, an executive with the Tennessee Board of Regents, explains his invention.
TRISTAN DENLEY: So what it does is it takes all of the grades for all of the students who have been at that institution before for the last, let's say, half a dozen years, and then takes your academic grades and then combines those to be able to make estimates for how you would do if you would take each of these classes. And then the thing is the predictions are pretty accurate.
FARMER: Yes, with this program, you can basically see what grade you'll make in advance. Now hold up, some people have told Denley, college isn't about finding the easiest path. It's about broadening your horizons and challenging yourself. Denley says, sure, for some.
DENLEY: But there is a real sense in which academic curiosity is a luxury that lots of people simply cannot afford.
KIYA JORDAN: I ended up taking basically, when it was all said and done, a whole year of classes that wasn't needed.
FARMER: Kiya Jordan went back to school for an associate's degree in health care coding. She says if her scholarship runs out early, she won't be able to pay her own way to finish.
JORDAN: It's frustrating. It's disappointing.
FARMER: It's a headache for institutions, too, who are increasingly scrutinized for their graduation rates. A Canadian data company called Desire2Learn, which already works with dozens of universities around the globe, has licensed Degree Compass for its profit potential. CEO John Baker won't say exactly how much he's charging colleges but he says the program could end up paying for itself.
JOHN BAKER: We know as more students complete and attain the results that they're looking for, the universities see more revenue coming into the university. And what we're trying to do with this technology is make it affordable.
FARMER: And like that, picking college courses becomes the latest choice where computers seem to know us better than we know ourselves. For NPR News, I'm Blake Farmer in Nashville.
NPR transcripts are created on a rush deadline by Verb8tm, Inc., an NPR contractor, and produced using a proprietary transcription process developed with NPR. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR’s programming is the audio record.