Arizona University uses card data to predict student dropout rates
Back in 2004, I was about to abandon my degree in Psychology after just a year. The course was a lot more statistics-based that I’d originally anticipated, and I missed the days when counting page numbers was the most maths I had to grapple with on any given day. I subsequently reset my university career with an English Literature twist.
While this might have been predictable to anyone who knows me and my relationship with numbers, I may well have been leaving other traces of my dissatisfaction if staff had only known where to look – not just in the papers I turned in, but in my whole attitudes to the campus and the way I engaged with others in that ill-fated year. Nowadays we have the technology to do that seamlessly, and that’s exactly what the University of Arizona is doing in a bid to catch dissatisfied students before they quit.
Students at the university receive a CatCard upon arrival – it’s a form of student ID which grants access to nearly 700 locations on campuses from their hall of residence and the library to the various snack machines dotted around the place. This provides a lot of information which, when combined with other data points, presents an overall picture of student wellbeing and can importantly offer clues as to whether a student is thriving or struggling in their new life. Having gathered freshman data over the course of three years, the university has managed to create an algorithm that predicts who is close to dropping out with an 85-90% accuracy – up from 73% based on just students’ known academic and personal metrics alone.
“By getting their digital traces, you can explore their patterns of movement, behaviour and interactions, and that tells you a great deal about them,” says Sudha Ram, a professor of management information systems who spearheads the initiative. These behaviours, according to Ram, may include shrinking social circles or unpredictable behaviour patterns.
“It’s [the CatCard] really not designed to track their social interactions, but you can, because you have a timestamp and location information,” explains Ram. So, for example, if student A is stamped as being at the coffee shop regularly at the same time as student B, you can reasonably assume they’re friends who catch up often.
“There are several quantitative measures you can extract from these networks, like the size of their social circle, and we can analyse changes in these networks to see if their social circle is shrinking or growing and if the strength of their connections is increasing or decreasing over time,” Ram explains.
While well intentioned, it’s clear that some students will feel uneasy that their data is tracked and used in this way, although this data is anonymised, Ram says: “Almost every prediction we make is personalised, without knowing who the individual is.”
In other words, she would personally not be able to identify any student by name, ID or anything else, but obviously, students eventually have to be identified to the relevant advisors for an intervention to be made. The CatCard policies website makes no mention of the data being used in this way, so we’ve contacted the university to ask about the data privacy measures in place – we will update this piece when we hear a response.
Nonetheless, it’s clear that knowing students may be struggling can make all the difference and could literally change lives. Ram has found that to stand the best chance of retaining struggling students, early intervention is key: whether it’s a time-management seminar or an invitation to social functions. “We think by doing these interventions by the 12th week, which is when students make up their mind, you’re sort of doing what Amazon does — delivering items you didn’t order but will be ordering in the future.”
That’s not quite what Amazon does – unless everyone but me has been receiving stuff they never ordered – but I take the point. “It’s all about thinking about the future,” Ram says. “It’s about planning for the future and making sure you’re doing things in a way that enables the future to happen the way you want it — for everyone’s benefit.”