Large amount of data have been collected routinely in the course of day-to-day work in different fields. Typically, the datasets constantly grow accumulating a large number of features, which are not equally important in decision-making. Rough set theory (RST)recently becomes very popular in dimensionality reduction and feature selection of large datasets. The RST approach to feature selection is used to determine a subset of features (or attributes) called reduct which can predict the decision concepts. In reality, there are multiple reducts in a given information system used for developing classifiers, amongst which the best performer is chosen as the final solution to the problem. Selecting a reduct with good performance is time expensive, as there might be many reducts of a given dataset. Therefore, obtaining a best performer classifier is not practical rather ensemble of different classifiers may lead to better classification accuracy. However, combining large number of classifiers increases complexity of the system. The work trades off between these two approaches and creates an efficient ensemble classifier.