Jurnal SIMADA (Sistem Informasi dan Manajemen Basis Data)
Vol. 8 No. 2 (2025): Jurnal SIMADA (Sistem Informasi dan Manajemen Basis Data)

ANALISIS DAN PREDIKSI KINERJA PEGAWAI DENGAN ALGORITMA KNN DAN SVM DI DINAS PENDIDIKAN PROVINSI LAMPUNG

Hasanah, Neneng Uswatun (Unknown)
Sri Lestari, Sri (Unknown)



Article Info

Publish Date
06 Oct 2025

Abstract

Employee performance assessment is a crucial factor in improving the quality of public services in government institutions. This study aims to analyze and predict employee performance at the Education Office of Lampung Province by utilizing the K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) algorithms. The KNN method was chosen for its ability to classify data with high accuracy for small to medium-sized datasets, while SVM was used due to its advantages in handling high-dimensional data and optimal classification margins. The dataset used includes employee performance evaluation data with variables such as attendance, productivity, discipline, and competence. The research process consists of data collection, preprocessing, model training, algorithm performance evaluation, and interpretation of results. The findings indicate that both algorithms can provide adequate predictions of employee performance. A performance comparison between KNN and SVM shows that SVM achieved higher accuracy than KNN for this dataset. These results are expected to serve as a reference for the management of the Education Office of Lampung Province in making decisions related to human resource development and strategies to improve employee performance. Keywords— Employee Performance, KNN, SVM, Prediction, Data Mining, Education Office of Lampung Province

Copyrights © 2025






Journal Info

Abbrev

SIMADA

Publisher

Subject

Computer Science & IT

Description

1. Sistem Informasi ((Human Computer Interaction, E-Business, E-Government, Decision Support System (DSS), Enterprise System, dll) 2. Manajemen Basis Data (Business Intelligence, Big Data, Data Warehouse, Distributed Database, Data Mining, Information Retrieval, Knowledge Management System, ...