Performance Comparison and Optimized Algorithm Classification

Abstract

Abstract The current development of technology is quite rapidly not disengaged in a large data processor covering of all areas such as information technology, computer science, medicine, finance and other. This brings a large computing effect in identifying the processing of data. In data analysis for very large data, data processing is very much needed, in this study the authors propose data mining method as a solution to a large data processing problem, data mining is divided into several techniques including classification method techniques that aims to classify large amounts of data to be relevant data information. In this study the authors compared 5 algorithms in the classification method to get better performance in classification problems. Researchers analyze and test 5 Algorithm classifications with 4 different datasets as a tool in the problem of large data classification. The results of this research show the method SVM is much better to be used 4 comparison methods in calculating the value of AUC by using 4 datasets of UCI Repository. The LSVT Dataset shows the highest AUC value with 0973, Ionsphere 0887, Sonar 0897, Heartstatlog 0868.