Civitas Learning’s dedicated team of data scientists create predictive algorithms to deliver powerful insights about your institution’s student data.
For Inspire for Advisors, the process is as follows:
- Civitas Learning ingests data from your sources and creates additional data points, called derived variables.
- After historical data is collected and new data variables are derived, students are grouped together based on what data are available for them. For example, a new student would not have a GPA, but a continuing student would. This process is called data availability segmentation.
- After segmentation, students with similar values for key data points are further grouped into clusters.
- Next, the most predictive variables for each student cluster are identified. This is known as variable optimization. These data variables are included in a predictive model for each student cluster.
- The results are multiple institution-specific predictive models using the most predictive variables for each unique cluster. Each model is tested on a student data set to ensure accuracy and validity.
- After testing, these models are ready for use with your active students. We ingest current student data from the same sources and apply our predictive models to deliver an individual persistence prediction for each student.
- The prediction is fed into Inspire for Advisors and appears as a colored bubble representing the student’s likelihood to persist. These predictions are refreshed on a frequent basis.
- Persistence probability is an objective measure calculated for each student based on the institution-specific persistence models. Over time, if students' behaviors change, their persistence probabilities will shift accordingly.