Predictive Analysis-Recruitment in schools

Predictive Analysis- College Recruitment

Every year schools and colleges across the globe are flooded with applications to their various programs of study. Most colleges have a separate department consisting of many enrollment managers to screen the prospective candidates and handle the large volume of applications in a timely manner. This involves a lot of effort and money spent on the recruitment process. Although this is a very important area of focus for each university the ‘screening’ process can become a lot easier by implementing predictive analysis. Most schools across the globe are now adopting various strategies to handle the large volume of applicants. This is an area where predictive analysis can be successfully implemented and used to save time and money. The technique of predictive analysis can be applied to different companies on a slightly different model who are also faced with numerous applicants. It can be used to perform ‘data-informed’ decisions. This is based out of an interesting article which talks about a certain technique which helps make the recruiting process more efficient by focusing the limited resources available. This technique in particular is very important as schools might give out admits, but if the candidate choses to reject the initial offer, the school loses a lot of valuable time spent on that candidate profile and most importantly another prospective candidate loses out on an opportunity.
Predictive modeling for enrollment is an inherently action-oriented process. It takes your previous enrollment data, applies it to prospective students, and provides an assessment of each student’s likelihood of enrolling. Every student receives a score from 0.00 (extremely unlikely to enroll) to 1.00 (extremely likely to enroll). This is based on overall candidate profile. For example a candidate with an exceptional profile exceeding school requirements would be low on this score, as he would get accepted in a school with a slightly higher requirement. This also depends on various other parameters. For example you could have your internal criteria for the entering class as say, 97 percent of the enrollments for came from students with a model score of .6 or higher. Some of the most important points highlighted in this article are mentioned below.
1. Purchase student names with high model scores. This allows you to shortlist names of those students who are more likely to enroll at your institution, eliminating potential waste by not focusing on students who will never enroll at your institution.
2. Load the highest scoring names directly into your inquiry pool. Many of our campus partners will take a sub-set of their purchased list and treat them as inquiries. The value of the predictive modeling score is that you can accurately pinpoint which students are most likely to enroll.
3. Segment your messaging by model score. Consider putting your search names into different buckets by score range. The highest model score students might receive the most robust communication flow (including written and electronic). Those with lower scores may receive a series of e-mail messages.
This kind of qualification means that schools can better focus their energy, effort, and resources on those inquiries who are more likely to enroll.
Several benefits from adopting this strategy include saving money on expensive mailings. Students in the lower score bands will enroll no matter what, hence communication via email is sufficient. Stronger relations can be built with prospective students and also speed the enrollment process.
References: Campuses using Predictive analysis- Sarah Coen
http://blog.noellevitz.com/2012/03/01/campuses-predictive-analytics-focus-college-student-recruitment-strategically/#disqus_thread