The Development of Artificial Neural Network Model for Predicting Optimal Job Position in Quality Control Station

The workforce in the manufacturing sector often works that do not match their competencies or are transferred to unskilled jobs such as quality control employees, leading to prolonged training periods and increased inefficiencies. This study aims to address this issue by analyzing the required employee competency by skill mapping. The competency dataset was obtained through the researcher's evaluation and job description documents, classifying the employees' knowledge and hard skills. An artificial neural network model was developed to predict the employee position in the new product quality control station. The study utilized the perceptron neural network algorithm for supervised learning in machine learning. The attributes were knowledge and hard skills and were divided into training and testing sets. The model was trained using RapidMiner program and its performance was measured using a confusion matrix. The results of using confusion matrix in the development of this prediction model resulted an accuracy of 82.00%