A Comparative Study to the Bank Market Prediction

Abstract

Bank market prediction is an important area of data mining research. In the present scenario, we are given with huge amounts of data from different banking organizations, but we are yet to achieve meaningful information from them. Data mining procedures will help us extracting interesting knowledge from this dataset to help in bank marketing campaigns. This work introduces analysis and applications of the most important techniques in data mining. In our work, we use Multilayer Perception Neural Network (MLPNN), Decision Tree (DT) and Support Vector Machine (SVM). The objective is to examine the performance of MLPNN, DT and SVM techniques on a real-world data of bank deposit subscription. The experimental results demonstrate, with higher accuracies, the success of these models in predicting the best campaign contact with the clients for subscribing deposit. The performance is evaluated by some well-known statistical measures such as accuracy, Root-mean-square error, Kappa statistic, TP-Rate, FP-Rate, Precision, Recall, F-Measure and ROC Area values.