Data-driven decision-making for the student lifecycle

Higher education is a relatively late adopter of predictive analytics as a management tool. Predictive analytics has been used in other industries for many years, especially in the area of assessing consumer behavior. For instance, automobile manufacturers and dealers use predictive analytics to assess the likelihood of a customer who leases a car to either purchase the vehicle or choose to lease a new vehicle at the end of the lease. Using predictive analytics, BMW might extend an offer for a no-penalty early lease termination to select customers who the data suggests are likely to move to Mercedes Benz or Audi, if they agree to a new BMW lease. In this scenario, offers would not be made to customers who the data suggest are predisposed to continue with BMW; instead, they are designed to generate repeat business from those most likely to defect.

In a similar way, colleges and universities can deploy predictive analytics to determine which students are most at risk for attrition and – armed with deep, historical data – craft segment-specific retention strategies designed to compel them to persist toward degree completion.

This white paper is designed to explain predictive analytics, followed by a look at how it can impact activity at the highest levels of institutional management. We provide examples of how predictive analytics has been used at a variety of institutions, including a review of its potential pitfalls and benefits. Citing interviews with practitioners, this white paper provides concrete examples of how predictive analytics has led to measurable performance improvements. Finally, we close with a call to action to all colleges and universities to consider building predictive analytics into their toolbox of techniques that inform and enable evidence-based decision-making.