- Data Services - Define...Clean…Enrich
- We work with you to cleanse your data and to streamline your processes so that you get the most for your student marketing budget.
- Analytic Services - Profile...Target...Test...Measure
- We customize a plan based on your institutions unique needs to deliver customized analytic solutions that make the tough decisions easy.
- Predictive Analytics - Predict…Identify…React
- By using the past to predict the future, enrollment managers can be more proactive and strategic.
Predictive Modeling – a process that uses historical information collected about an event to create a model that is used to predict the probability of an outcome. By using the past to predict the future, management can be more proactive and strategic.
Recruitment Modeling – describes a model that is used to identify prospective students that are most likely to inquire, apply or enroll. Recruitment modeling drives efficient and effective campaign performance while revealing the factors that influence prospective student’s enrollment behavior. A score is generated for each prospective student that identifies the likelihood of a desirable outcome based on intelligence derived through data mining. In addition a rank is assigned that provides the enrollment manager an actionable output from the model. Upon reviewing a gains chart of observed results by rank, the enrollment manager may create various strategies for communicating with the various ranks. Resources may then be focused on those who elicit the greatest potential for inquiring, applying or enrolling.
Retention Modeling – describes a model that is used to identify students that are most likely to drop or stop out? Since it is widely accepted that the cost of retaining an existing student is far less than acquiring a new one, retention modeling can deliver great value. Retention models are similar in structure to Recruitment models, with the objective (or dependent variable) shifted to focus on retention. The retention model will score and rank students based on their likelihood to stop or drop out, allowing for targeted retention efforts. Much intelligence is also revealed regarding the factors that lead to a student’s dropping or stopping out.