Analyzing and clustering students' application preferences in higher education

Area of Science:

• Educational Data Mining
• Higher Education Analytics
• Socioeconomic Analysis

Background:

• Analyzing higher education application data is crucial for understanding student enrollment trends and institutional strategies.
• Traditional methods may lack the flexibility to capture nuanced applicant preferences.
• Understanding regional disparities in higher education access is an ongoing challenge.

Purpose of the Study:

• To develop and validate a novel framework for flexible aggregation and analysis of higher education application data.
• To investigate the influence of center-periphery dynamics on application preferences.
• To assess the tractability of influencing student preferences in higher education admissions.

Main Methods:

• A framework based on converting higher education application preference lists into quantifiable scores.
• Flexible aggregation techniques for analyzing clustered application data.
• Empirical application using Hungarian higher education data from 2006-2015.

Main Results:

• The proposed method allows for flexible aggregation and clustering of application data.
• Analysis reveals that strategies aiming to leverage center-periphery differences in higher education applications did not meet expectations.
• Student's top preference in higher education applications is highly resistant to external influence.

Conclusions:

• The developed framework offers a flexible approach to higher education application data analysis.
• Geographical or socioeconomic center-periphery strategies appear ineffective in shifting applicant preferences.
• Recruitment strategies should prioritize understanding and leveraging information on students' first and second preferences.