Higher classification accuracy of income class using logistic regression algorithm over naive bayes algorithm.

The aim of the study is to perform higher classification of Income Class Classification by implementing innovative income classification for individuals above and below 50k income using machine learning classi fiers by comparing them. The two groups such as Logistic Regression Algorithm and Naive Bayes Algorithm. The algorithms have been implemented and tested over a dataset which consists of 32516 records. Through the programming experiment that has performed N=10 iterations on each algorithm to identify various scales of income class for above and below 50k income classification. The G-power test used is about 80%. The results of the experiment, the mean accuracy of 79.6410 by using Logistic Regression Algorithm and the accuracy of 79.3170 by using Naive Bayes Algorithm for income class classification. There is a statistically insignificant difference in accuracy for two algorithms is p>0.05 by performing independent samples t-tests which is 0.683 and hence it is insignificant. This research article is intended to implement an innovative approach to recent Machine Learning Classifiers for income prediction class classification. The comparison results show that the Logistic Regression Algorithm has better performance when compared to Naive Bayes Algorithm. [ABSTRACT FROM AUTHOR]