An ML-based solution helps a top B School increase yield rates by 18%

About

The client is one of the top 20 B-Schools in the USA offering full-time, online and executive MBA courses.

Challenges

  • The B-School was having a low yield rate since many applicants opted for admit offers from other schools. This process also impacted the quality of student intake.
  • The client was also investing heavily in marketing and student recruitment activities amounting to over 7% of its revenues.
  • The entire process of identifying the right candidates based on over 200+ parameters was manual and repetitive.

Solution

Tenzai deployed the purpose driven AI approach to develop a machine-learning based solution to identify the right candidates to admit. 

Data from multiple sources like application data, clickstream data, campus visits, and test results were integrated to create a 360 view of applicants. An in-depth exploratory analysis helped the client develop different applicant genome profiles.

An in-depth exploratory analysis was conducted to explore key insights to identify the typical profile of applicants. Attributes like education, professional experience, test performance, demographics and other attributes were considered for the analysis. The analysis helped the client to identify the behavior of candidates who are most likely to accept their admit offers.

Then using machine learning and ensemble techniques a lookalike or clone model was built. This model helped the client to identify applicants having a high propensity to accept their offers. The propensity scores helped the admission teams to prioritize applicants more efficiently.

Why not use data to gain insights, guide efficiency efforts, and make predictions? Contact us.

Results

The integrated machine learning admission prediction solution was deployed in the customer’s cloud environment and integrated with the existing CRM and admission workflows.

The new ML model helped the client to increase their yield rate significantly by identifying the right applicants and prioritizing them for admit offers.

Key benefits include:

  • The ML model helped the client increase the yield rate by 18%
  • Due to in-depth insights into applicant profiles, the B-School was able to reduce its marketing expense by 14%
  • The solution was able to increase the efficiency of the admission team by 3X.