<![CDATA[Credit analysis needs to identify and assess factors that can influence customers in credit returns. Accurate measurement and good management capability in dealing with credit risk is an effort to save the economic operations unit and is beneficial for a stable and healthy financial system. Failure to identify credit risk results in loss of income and extends credit risk to a bad type of threat to profitability. Data mining prediction techniques are used to determine credit risk. Using the Cross-Industry Standard Process for data mining CRISP-DM. This study has tested the model using a neural network using PCA feature selection and optimized with the PSO algorithm to predict credit card approval. Several experiments were conducted to see the best results. The results of this study prove the use of a single Neural Net method produces an accuracy of 80.33%. while the use of the hybrid PCA+NN+PSO method has been proven to increase accuracy to 82.67%. Likewise, the AUC NN value of 0.706 increased to 0.749 when the NN was optimized using PSO and using the PCA. This study implements and compares PCA-based SVM, L. Regression and NN algorithms and optimize PSO to improve accuracy in credit card approval predictions.]]>
Copyrights © 2019
