3 Ways Big Data Can Soften the Campus Dropout Crisis

Debt without degrees: That’s the reality facing more than half of all young people entering four-year colleges — they seemingly vanish from university rolls into the vapor of attrition.

Instead of tossing mortarboards into the air come June, these non-graduates face a rocky climb in the job force, where they scramble to make up for their educational gaps.

Not only is the higher education retention struggle a crisis for the country’s future professional workforce, but it’s also an immediate concern for public and private educational institutions.

And like any major problem, this mass exodus of dropouts must be addressed sooner rather than later through innovative interventions. Sweeping the issue under the rug makes no sense; hitting it head-on with technology does. Enter the use of big data and predictive analytics.


While many universities have begun to dabble in the realm of big data and predictive analytics, they often limit their use of these tools to evaluating academic performance as a major predictor of attrition. Even online schools, where data can be more available due to vibrant learning management systems, are guilty of merely scratching the surface of data capture and analysis.

What’s being missed? The “soft” predictors, those subtle hints that are precursors to student dropout. These clues exist not just in classroom performance or student transcripts, but also on social media sites and in other virtual landscapes. To be sure, not all university personnel are eschewing social platforms’ value; Kaplan’s study in 2015 suggested that 40 percent of surveyed institutions based potential freshman acceptance rates partially on candidates’ web social interactions. Still, universities could be using social cues more effectively.

Seem a bit like “1984” coming to life? It’s less invasive than it sounds.


[RELATED]: Tech Hacks That Help Higher Ed Pros Cut Costs (and Keep Students)

Let’s face it: Big data already exists in droves — and it’s publicly available for campuses that take the time to look. From the friends and followers potential students tout on their social feeds, to the number of times incoming freshmen buy supplies or food on campus using a swiped ID card, the data is ripe for the picking.

In fact, the sheer breadth of student-based data is absolutely staggering. Without a doubt, every touchpoint has the potential to play a key role in the predictive analyses of student retention. The goal? Capture the data, then understand how to use it accurately to lower attrition rates, which affect institutions’ pocketbooks anywhere from 9 to 33 percent annually. Ironically, an attrition improvement of just 1 percent could cascade to a billion-dollar influx in the community a given institution serves.


Physics 101 tells us a body in motion tends to stay in motion, while a body at rest remains at rest — in other words, the sooner you dive into big data, the easier it will be to keep going. Here’s how to get started:

To learn three ways to begin using big data and predictive analytics to foster student retention, please read the full article on EdNews Daily.