IMPLEMENTASI ALGORITMA K-NEAREST NEIGHBOR UNTUK OPTIMASI PEMBERIAN REWARD SISWA SMA

Abstract

Providing rewards to students is a common strategy to enhance learning motivation and participation in school. However, conventional reward systems often face challenges related to objectivity and the comprehensiveness of assessment criteria. This study aims to apply the K-Nearest Neighbor (KNN) algorithm as an optimization tool for determining reward recipients among high school students. The dataset includes average report card scores, moral values, parental income, number of siblings, and non-academic activity scores. The KNN method was selected for its effectiveness in classifying data based on similarity. The research process involved collecting historical student data, normalizing the data, building the KNN model, and evaluating its performance. The results show that the KNN model achieved an accuracy rate of 91% in classifying students into appropriate reward categories. This indicates that the model can reliably support decision-making in the reward distribution process. In conclusion, applying the KNN algorithm offers a more structured, objective, and transparent approach to student reward allocation, which can enhance the effectiveness of reward programs and promote student development.

Keywords: K-Nearest Neighbor, Reward, Classification, Objectivity, Optimization