Capture Blog

Introducing Envision: Next Generation Predictive Modeling for Colleges

Multiple machine-learning algorithms … Rapid iteration … More accurate predictions … Smarter decisions …

With Envision, Capture Higher Ed has released higher education’s first ensemble predictive model, unique to the enrollment management industry because it combines various machine-learning algorithms to build ensemble predictive models for application, enrollment and financial aid.

Unlike current predictive models in higher education, which are built upon historical data and not easily iterated upon, Capture’s patent-pending models utilize machine learning and multiple algorithms to continuously look for patterns and make more accurate predictions every time new data becomes available.

According higher education research firm, Noel-Levitz, nearly 73 percent of four-year private institutions are using a statistical model to help predict enrollment outcomes annually. But those predictions are grossly inaccurate. Only 39 percent of colleges and universities actually hit their enrollment goals in 2015.

Since Envision’s launch last summer, Capture has signed 18 partners that integrate this critical intelligence into their student recruitment practices. As a tool, it can be used in different ways. Large public universities like the University of Minnesota and the University of Tennessee as well as smaller privates like Suffolk College and Elmira College have opted to use the engine for individualized student aid models and enrollment prediction models.

Much of the work at Capture involves building the tools that make our partner’s work easier, more reliable, and most important — more accurate. And accuracy is exactly what Envision provides.

Empirical data shows that in the past 12 months, Capture’s application models are on average 90 percent accurate, and their enrollment models are 97 percent accurate. This is invaluable information for enrollment offices, allowing them to target their marketing toward students who are most likely to enroll instead of wasting those resources on students who have no intention of enrolling.

Capture’s accurate application models show that the top two deciles of a potential student pool enroll at five times the rate of all other applicants. Admissions offices can take this information and directly affect cost savings by reducing or eliminating pricey tactics like direct mail and calling campaigns to students in the bottom deciles — those who are least likely to apply.

In some instances, it can save an institution 80 percent of previous year’s per-student marketing spend.

In the case of one institution in central Ohio, Capture provided the potential partner with their Envision application model details, and the insights showed that in the top decile they could accurately recruit over a thousand students at $54 as compared to $3,792 per student in the bottom decile. With this knowledge, the college can effectively save thousands of dollars towards their marketing efforts.

Envision also has significant potential when it comes to the intricacies of offering financial aid. With high accuracy, the software can suggest individualized student aid offerings to financial aid directors­ — helping them navigate the complicated waters of institutional aid offering.

The National College Access Network reported that 85 percent of first-time, four-year degree seeking students received some type of aid in the 2015-2016 academic year. Nearly 22 million students requested some type of institutional or federal aid, up 33 percent from just five years ago.

With the average institutional discount rate approaching 50 percent and the cost to recruit a student up 34 percent from 10 years ago, dollars on marketing or financial aid must be spent more wisely.

Capture is building products to do just that. As a data-thought leader in the higher ed industry, the tech start-up will continue to aid its partners in making smarter, more accurate decisions that directly affect a college’s bottom line.

See for yourself how Capture uses logistic regression, multiple types of data, automatic feature selections, dynamic scoring as well as how we can retrain your model within the enrollment cycle. Sign up for a Envision Trial and let us run your data for free. We’re eager to show you what we can do.

By Ellen Stubbs, Vice President of Marketing, Capture Higher Ed

Share this!Share on FacebookTweet about this on TwitterShare on Google+Share on LinkedIn
Please wait...

Subscribe to our weekly blog digest!

You will get fresh weekly content, and we will never sell your email.