Data mining (DM) is the process of retrieving information from huge data-sets and transforming them into meaningful decision. Classification technique is considered to be the most important data mining techniques as it becoming an enthralling topic to the scholars that precisely and effectively describes data for the knowledge-discovery. It is used to describe and distinguish data classes or concepts. There are two major classes of classification problems: Binary-class and Multi-class. In Binary-class classifications, the given data-set is categorized into two classes whereas in Multi-class classification, the given data-set is categorized into several classes based on the classification rules. This paper explores several DM classification approaches such as Decision tree like Classification and Regression Tree(CART) and Conditional Inference Tree(CTREE), Random Forest(RF), Support Vector Machine(SVM) and k-Nearest-Neighbour(KNN) to enhance the result of binary class and multi-class classifiers using the powerful Big data mining analytical tool R and RStudio. Various measures such as Accuracy, F-Score, Sensitivity etc. are used to evaluate the classifier’s performance and also predict which classifier will perform better when the training-testing data-sets are analysed with multiple partitions (%).