Mining a Marketing Campaigns Data of Bank

In this paper, we propose a data mining approach to predict the success of telemarketing. We are applying the algorithms for the first time on the dataset. The dataset obtained from UCI, which contain the most common machine learning datasets. The data is related to direct marketing campaigns of a Portuguese banking institution. The marketing campaigns were based on phone calls. Often, more than one contact to the same client was required, in order to access if the product (bank term deposit) would be ('yes') or not ('no') subscribed. The number of the instance is 45212 with 15 input variables and the output variable. Classification is a data mining techniques used to predict group membership for a data instance. we present the comparison of different classification techniques in open source data mining software which consists of a One-R algorithm methods and Naïve-Bayes algorithm The experiment results show are a bout classification sensitivity, specificity, accuracy. The results on bank marketing data discovered that the One-R algorithm is better in classifying the data comparing with the Naïve-Bayes algorithm; where the error rate is lower.