Support Vector Regression for Modeling Effect of Education Rate on Life Expectancy Rate in Indonesia

Abstract

Life Expectancy Rate is the average number of years of life that is lived by someone who has reached a certain age. Life Expectancy is a tool to evaluate the government performance in improving the prosperity of the people. Studies on the factors that influence Life Expectancy Rate are needed to reach more accurate mathematics model to provide a better consideration for the government to determine the direction of future development policies. The data used in this study were derived from SUSENAS data with the objects of observations are all districts/cities in Indonesia in 2012. In this research, Support Vector Regression (SVR) method is used to estimate the effect of education factor which is represented by length of education by years (X) on Life Expectancy Rate (Y). Support Vector Regression (SVR) model in this research used several different kernels such as  polynomial kernel, RBF and Exponential RBF (ERBF) to find the best model. The best model criterion is the model that produces the largest R2 value. The best model resulted in this research is a model that uses Exponential RBF kernel.