Data-Driven Decision Making in Scholarship Programs: Leveraging Decision Trees and Clustering Algorithms

Abstract

This study presents a unique and innovative approach to improving the management of scholarship programs through the integration of data mining techniques and online systems. The BRO-Ed Scholarship program in Isabela province is facing the challenge of efficiently handling a growing number of scholarship applications. This study involves leveraging data mining to simplify this process, address operational challenges, and contribute to the transformation of the lives of underprivileged students. Data mining techniques that include systematic data integration, preprocessing, decision tree implementation, and clustering algorithms were utilized in this study. Additionally, we have created a user-friendly online platform to enhance accessibility. Initial results show a significant increase in the success rate, indicating the potential of managing scholarships using data-driven approaches. The expected outcomes include a streamlined application process, informed decisions based on data-driven analysis, and optimized budget allocation. By establishing a model for innovative advancement in scholarship programs, this project aims to promote educational support initiatives for underprivileged students aligned with the government’s mandate for Sustainable Development Goal 4, addressing growing inequality among marginalized people and communities.

Keywords: Data Mining, Decision Trees, Clustering Algorithm, Scholarship Programs, Underprivileged Students, Sustainable Development Goal 4

Received Date: March 2, 2024
Revised Date: April 22, 2024
Accepted Date: May 4, 2024