Predictive data mining is the process of automatically creating a classification model from a set of examples, called the training set, which belongs to a set of classes. Once a model is created, it can be used to automatically predict the class of other unclassified examples. Some datasets encountered in real life applications have skewed class distributions. Many predictive modeling systems are not prepared to induce a classifier that accurately classifies the minority class under such situation. In this work, an attempt has been made to build the predictive model for delinquency in credit cards users, using the state of art methods. The success of the model is defined in different terms than the ones found in literature. Different sampling schemes are evaluated and a modified naive Bayes classifier is used as classifier. The results are encouraging and it is proposed to compare the prototype with ensemble of models.
