Decision trees are said to be one of the most efficient and scalable algorithms to map data observations about an item to derive conclusions corresponding to the items target value. A decision tree is used to build classification model in the form of a tree-like structure based on certain condition with class-labeled training tuples. The evolution of decision tree algorithm has different variants based on the functionality and parametric evaluation. The execution of decision tree depends on the splitting criterion, which specifies how the split has to be made in accordance with the input attributes and the class label is determined. The attribute selection measure gain ratio is used up for generating the decision tree for data classification. The utilization of decision trees has been reported majorly for the cases corresponding to data classification and prediction. It is widely used in different sorts of applications for both discrete and continuous valued attributes.