Klasifikasi Tingkat Pendidikan Karyawan Menggunakan Algoritma C4.5

Abstract

The rapid development of information technology has encouraged organizations to utilize data as a strategic asset for decision-making, particularly in human resource management (HRM). One important aspect of HR management is analyzing employee characteristics, including education level and employee turnover tendencies. This study aims to apply the C4.5 Decision Tree algorithm to classify employee data in order to predict employee turnover based on various supporting attributes. The dataset used consists of 4,652 employee records with attributes such as education level, age, city, salary tier, gender, joining year, work experience, and bench status. The research stages include problem identification, literature review, data collection, data preprocessing, implementation of the C4.5 algorithm, and model evaluation. The modeling process was conducted using RapidMiner with a data split of 90% for training and 10% for testing. The results show that the C4.5 Decision Tree model achieved an accuracy of 75.86% with a classification error of 24.14%. The decision tree visualization indicates that PaymentTier, Age, City, Gender, and Education are the most influential attributes in predicting employee resignation. Although the model demonstrates satisfactory performance as a baseline and offers good interpretability, further improvements are required to enhance its sensitivity in detecting employees at high risk of leaving the company.