Peer Review Jurnal Performance Comparison of Data Mining Algorithm to Predict Approval of Credit Card

Abstract— Credit analysis needs to identify and assess the factors that can affect

customers in returning credit. Accurate measurement and good management ability in

dealing with credit risk is an effort to save the economic operations unit and be

beneficial for a stable and healthy financial system. Data mining prediction techniques

are used to determine credit risk. Using the Cross-Industry Standard Process for Data

Mining (CRISP-DM) method which consists of several stages, namely Business

Understanding (dataset), Data Processing (Feature Selection Principle Component

Analysis & Dimension Reduce), Algorithm Models (Neural Network + Particle Swarm

Optimize, Support Vector Machine, Logistic Regression), Evaluation (Validation and

Accuracy). This study has tested the model using a neural network using the Principle

Component Analysis (PCA) selection feature and optimized with the Particle Swarm

Optimize (PSO) algorithm to predict credit card approval. Several experiments were

conducted to see the best results. The results of this study prove that the use of a single

Neural Network method produces an accuracy of 80.33%. whereas the use of PCA +

Neural Network + PSO hybrid method has been proven to increase accuracy to 82.67%.

Likewise, the AUC NN value of 0.706 increased to 0.749 when the Neural Network was

optimized using PSO and used feature selection.

Unduhan