Comparative Study of Big Data Classification Algorithm Based on SVM

Abstract

Linear support vector machine (SVM) is one of the most effective machine learning methods to process large-scale data set. Based on the simple expatiation of the principle of support vector machine (SVM), linear support vector machine (SVM) and traditional support vector machine's training time and classification precision are compared and analyzed through the experiment. The results show that linear support vector machine has obvious advantages in terms of training speed and classification precision, which is a powerful tool to realize big data classification and regression. The experimental results show that for linearly separable data set, the LIBLINEAR toolkit is characterized by short training time and high classification precision, which is very suitable for large-scale data set classification.