Penilaian kinerja pegawai dengan metode TOPSIS dan backpropagation neural network

Yuliawan, Audi Bayu, Hariyadi, M. Amin ORCID: https://orcid.org/0000-0001-9327-7604, Kusumawati, Ririen ORCID: https://orcid.org/0000-0001-6090-7219, Crysdian, Cahyo ORCID: https://orcid.org/0000-0002-7488-6217 and Nugroho, Fresy ORCID: https://orcid.org/0000-0001-9448-316X (2025) Penilaian kinerja pegawai dengan metode TOPSIS dan backpropagation neural network. JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), 10 (2). pp. 1689-1696. ISSN 25408984

Preview

Text 23837.pdf Available under License Creative Commons Attribution Share Alike. Download (484kB) | Preview

Abstract

The digital transformation driven by Industry 4.0 and the implementation of e-Government has significantly reshaped the paradigm of public administration, necessitating a more adaptive and objective employee performance evaluation system. This study aims to classify employee performance into five categories: “excellent,” “good,” “fair,” “poor,” and “very poor,” using the Neural Network Backpropagation approach. The methodology consists of several key stages, beginning with data preprocessing that organizes evaluation criteria into four main aspects: qualification, competence, performance, and discipline. Subsequently, feature selection is carried out using the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), with the selected features employed as training data for the Neural Network Backpropagation model. The training results indicate satisfactory model performance, with a loss and Mean Squared Error (MSE) of 0,000465, a Mean Absolute Percentage Error (MAPE) of 19,59%, and an accuracy of 80,41%. Separately, experiments using the TOPSIS method alone yielded an accuracy of 81% and a loss of 0,377. The integration of TOPSIS and Neural Network Backpropagation demonstrates effectiveness in consistently classifying employee performance. These findings contribute to the development of an AI-based performance evaluation system that is both accurate and adaptive to the evolving challenges of modern public administration

Item Type:	Journal Article
Keywords:	TOPSIS; Neural Network Backpropagation; Penilaian Kinerja Pegawai; Industri 4.0; e-Government
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080105 Expert Systems 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing
Divisions:	Graduate Schools > Magister Programme > Graduate School of Informatics Engineering
Depositing User:	Mokhamad Amin Hariyadi
Date Deposited:	12 Jun 2025 13:45

Downloads

Origin of downloads

Actions (login required)

View Item