Principal Component Analysis and Bacterial Foraging Optimization for Credit Scoring

Abstract

Information technology in the current era is developing very quickly. Information systems themselves are found in various aspects of life, such as health, law, education and finance. With the improvement of information systems, systems can be created as considerations for making decisions or agreements. Credit scoring is a status that is usually held by banks or other financial institutions and contains data from debtors who have applied for credit at certain banks or financial institutions. There are many attributes in determining whether someone will get good credit or bad credit status. Therefore, a fast and accurate classification method is needed. This research proposes the use of Principal Component Analysis to reduce several attributes without reducing the attributes that are important or crucial in determining. This research also uses the Bacterial Foraging Optimization algorithm to optimize qualification results on the Support Vector Machine which uses 4 kernels, namely Linear, RBF, Polynomial and Sigmoid. The research results show that the Linear kernel accuracy which only uses Principal Component Analysis gets a value of 79%. Then optimized with Bacterial Foraging Optimization to get an accuracy of 81%. So the Bacterial Foraging Optimization algorithm increases accuracy by 2%. For RBF and Poly kernels, the accuracy is the same, namely 78%. For the Sigmoid kernel, it got the best results in Principal Component Analysis, namely getting an accuracy value of 80%.