Comparison of Clustering Methods for Mixed Data: A Case Study on Hypothetical Student Scholarship Data

View Full Paper

Ask AI

Bookmark

Authors

Discussion

This analysis finds high accuracy in clustering techniques for mixed data in scholarship data, suggesting the importance of method selection.

K-Prototypes achieved the highest accuracy at 95.6% in categorizing scholarship candidates, and PAM followed closely at 92.5%.
The hybrid K-Means method with FAMD provided a robust alternative with 93.9% accuracy, proving useful for mixed data applications.
Categorical variables significantly influence clustering outcomes, emphasizing their role in educational funding decisions.
The study highlights the need for suitable clustering techniques, particularly in the context of high-stakes scholarship selection.

Ataseven et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

This analysis finds high accuracy in clustering techniques for mixed data in scholarship data, suggesting the importance of method selection.