Prediction of civil servant performance allowances using the neural network backpropagation method

Kurniawan, Puan Maharani, Almais, Agung Teguh Wibowo, Hariyadi, M. Amin, Yaqin, M. Ainul and Suhartono, Suhartono (2023) Prediction of civil servant performance allowances using the neural network backpropagation method. JOIV : International Journal on Informatics Visualization, 7 (3). pp. 673-680. ISSN 2549-9610 / 2549-9904

Preview

Text 15853.pdf - Published Version Available under License Creative Commons Attribution Share Alike. Download (3MB) | Preview

Abstract

Performance allowance is a form of appreciation given by an agency to its human resources. The Office of the Ministry of Religion of Batu City provides performance allowances to civil servants who work in the agency. Several things that affect the provision of performance allowances, such as grade, deduction, taxable income, income tax, and total tax, are used in this study to produce the total gross performance allowances and total performance allowances received. Based on the data obtained, there are some missing data from the parameters of taxable income, income tax, and total tax. This study aims to predict performance allowance when there is missing data. The method used is Neural Network Backpropagation. This study uses 480 data with split data ratios of 50:50, 60:40, 70:30, and 80:20, with epochs 40,000 and a learning rate 0,9. Four types of models used in this study are distinguished based on the number of hidden layers and epochs used. Model A uses two hidden layers to produce the highest accuracy with a 50:50 data split ratio of 65,16%. Model B uses four hidden layers to produce the highest accuracy with a 50:50 data split ratio of 69,34%. Model C uses six hidden layers to produce the highest accuracy with a 50:50 data split ratio of 68,18%. Model D uses eight hidden layers to produce the highest accuracy with a 50:50 data split ratio of 70,90%.

Item Type:	Journal Article
Keywords:	performance allowance; neural network; backpropagation; prediction;
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing 08 INFORMATION AND COMPUTING SCIENCES > 0806 Information Systems 10 TECHNOLOGY > 1005 Communications Technologies
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	Agung teguh Wibowo Almais
Date Deposited:	23 Oct 2023 11:30

Downloads

Origin of downloads

Available Versions of this Item

• Prediction of civil servant performance allowances using the neural network backpropagation method. (deposited 23 Oct 2023 11:30) [Currently Displayed]

Actions (login required)

View Item