Problem Use Case
- A leading US university with 10,000+ students, collaborated with Canopus to identify profiles of students with high dropout risk so that appropriate interventions can be planned in a timely manner to maximize retention.
- Despite spending significant resources & effort on student reach out, the student dropout rate was continuously increasing.
- Students didn’t stay through the period, which affected the state funding to the university and also resulted in unutilized capacity within a program.
- It became hard for University to identify the drivers of early attrition.
- Canopus built predictive models leveraging advanced statistical methods that helped in
a. Selecting applicants with a higher retention propensity.
b. Identifying students with a significantly higher risk of dropping out.
- We performed in-depth analysis of all applicants and students; and developed couple of statistically robust predictive models that predicts high risk applicants and identifies “at-risk” students at various points of lifecycle.
- One of the models was useful to identify such applicants who were expected to leave within 3-6 months’ time.
- The other one helped to identify drop outs at the end of first year based on their performance and engagement during the first semester.
- It helped the university save approximately USD 180K of cost annually.
- Improved university reputation.