Improvement in Prediction Accuracy using Data Mining Techniques

Abstract: In today�s competitive world companies� aim is to maintain their customers. In the competitive environment, companies need to build their predictive models to identify their potential customer behaviors. Data mining techniques can be used to build the prediction model for companies because it can extract the predictive information from large databases. The accurate prediction helps in the growth of the industry. The prediction model is build by using Naive Bayes algorithm. But it is based on the independent assumptions between features. The objective of this paper is to improve the accuracy of prediction by using Data mining algorithm with a Naive Bayes Classier for better results. The proposed system gives the accuracy of 72.62% by using data mining techniques on UCI machine learning Repository which is a bank data set.

Keywords: Data Mining, Classification, Prediction, etc.