Kappa and accuracy evaluations of machine learning classifiers

Abstract

Machine learning is a method in which computers are given the competence to acquire without being unambiguously programmed. Machine learning discovers the learning and structuring of algorithms that can learn from the past data and make predictions on the same. Methods for relating two or more algorithms on a single dataset have been inspected in the current scenario, comparison of algorithms on multiple datasets is even more crucial for a typical machine learning studies. In this paper I have discussed about the Kappa and Accuracy Evaluations of Machine Learning Classifiers on multiple datasets. The objective of this paper is to compare and analyze the execution of these algorithms based on the efficiency of machine learning algorithms such as Classification and Regression Tree (CART), Linear Discriminant Analysis (LDA), k-Nearest Neighbor (kNN), Support Vector Machine (SVM) and Random Forest.