Comparative Analysis of Classification Methods in R Environment with two Different Data Sets

Machine Learning methods are widely used in various domains as they are influential in classification and prediction processes. The frequently used supervised machine learning task is classification. There are various types of classification algorithms with strengths and weaknesses appropriate for different types of input data. This paper depicts the implementation of few classification methods such as Decision Tree, K Nearest Neighbour and Naïve Byes classifier for different datasets in R environment. This paper presents the comparative study of these methods using open source tool R. The aim of this paper is to analyse the performance of these methods in two different datasets based on the evaluation metrics like accuracy and error rate. The implementation procedure show that the performance of any classification algorithm is based on the type of attributes of datasets and their characteristics. This paper shows that based on the constraints, requirements with type of input datasets specific algorithm and tool can be chosen for implementation.