<![CDATA[Discipline in the payment of tuition fees is an important aspect of school financial management, especially in private educational institutions. This research aims to optimize student grouping based on tuition payment discipline by applying the K-Nearest Neighbors (K-NN) algorithm integrated with the Entropy method as a feature weighting technique. The data used is historical data of tuition payments of students of SMK Diponegoro with attributes such as gender, number of siblings, profession and salary of parents, and status of aid recipients. After going through the preprocessing and normalization stages, the K-NN algorithm is applied with a value of K = 10 and distance calculation using Euclidean Distance. Test results with confusion matrix show an accuracy of 75.86%, recall 80%, and precision 61.54%. This proves that the K-NN algorithm optimized with the Entropy method is quite effective in classifying students into the “Right” or “Late” category in paying tuition fees.]]>
Copyrights © 2025
