Supervised Machine Learning Algorithms: Classification and Comparison Based on Experimental Analysis

Abstract

Data mining is a stage in the knowledge disclosure process comprising of data mining algorithms that used to discover patterns in the data. Data mining is used for finding hidden patterns in the database or any other information repository. The main task is to extract knowledge out of the information. Supervised learning algorithms determine the performance based on accuracy and time are considered as best way to classify the attributes of the dataset into different classes. In this paper, we use five supervised learning algorithms namely Naïve Bayes, Decision tree, Support vector machine, K-nearest neighbors and Artificial neural network for analyzing their performance using different parameters to finding the impact on the performance on different datasets. We compare the performance of each algorithm and then compare all five algorithms on different binary and multiclass datasets.