Student Data Analysis for Decision Making Using Decision Tree

Abstract

In today's digital era, data has become a valuable asset that supports effective decision-making in various fields, including education. In Indonesia, the education sector needs a technology-based strategy to utilize data optimally in improving the quality of education services. Data mining, as an information technology approach, plays an important role in extracting valuable information from big and complex data. Classification algorithms such as the Decision Tree, specifically the C4.5 algorithm, are widely used in data mining to build accurate decision models. This study aims to apply the C4.5 algorithm to student data to support evidence-based decision-making in education. Using RapidMiner software, this research focuses on classifying and analyzing student data to build a model that can simplify the decision-making process, making it easier to understand and implement. The results of this study show that there is a pattern of gender distribution in various classes, with some classes dominated by female students and others dominated by male students. The preprocessing stage successfully simplifies the data, so that relevant information can be analyzed more easily. These results underscore the importance of data mining technology in education data analysis for better decision-making, as well as provide new insights in designing data-driven education policies.