PREDIKSI CALON NASABAH GADAI POTENSIAL PADA PT. PEGADAIAN (PERSERO) MENGGUNAKAN SUPPORT VECTOR MACHINE DENGAN ALGORITMA GENETIKA

Abstract

PT Pegadaian is a company that offers business capital loans to customers by providing collateral or a pawn system. Customers who cannot repay loans and are in arrears are considered non-potential. Non-potential customers are harm the company because it reduces capital and profits. Statistical methods are needed to predict potential. Predictions are made using the classification method, in this research is Support Vector Machine (SVM). However SVM has a weakness in determining optimal parameters, so optimization is carried out using genetic algorithms to help find optimal classification parameters. Genetic algorithms are used to find optimal solutions to problems by imitating observed processes. This study uses customer data and proof of pawn PT Pegadaian Kebumen on January 3rd 2022 – November 29th 2022. The support vector machine model is formed with a percentage of 80% for training data and 20% for test data. The conclusion in this study was that SVM-GA increased the accuracy obtained from 86,6% being 94,2%.