To search, Click below search items.


All Published Papers Search Service


Performance Comparison of Data Mining Algorithms for the Predictive Accuracy of Credit Card Defaulters


Dr. Maruf Pasha, Meherwar Fatima, Abdul Manan Dogar, Furrakh Shahzad


Vol. 17  No. 3  pp. 178-183


The use of credit card for a secure balance transfer is a need of time. Fraudulent activities are also arising due to the fast growth of transactions. The motive of this research is to compare the predictive accuracy of customer’s default payments using different data mining techniques. Accuracy can be predicted in more compact form than just describing binary result classification of “Credible” or “Not Credible” in respect of risk management. Normally, “defaulters” actual chance of default is mysterious. Six data mining techniques (FLDA, Naïve Bayes, J48, Logistic Regression, MLP, and IBK) are applied to the data-set. The results of this research indicate that the neural network performs best to predict the default of credit card clients and shows the highest accuracy.


Data mining algorithms, Credit card defaulters, Performance of data mining, Predictive accuracy of credit card defaulters