<![CDATA[The problem of poverty has a critical role in social life, especially for the government associated with all forms of programs to eradicate poverty. The classification of low-income families also serves as a point to prioritize all forms of assistance in government programs. In these problems, it is quite apparent that the distribution of aid is not well-targeted. In this study, we are looking for for the classification method with the best performance in classifying low-income families. This study limits the classification method to the Naïve Bayes classification method and the k-Nearest Neighbor classification method. The dataset used is more than 800 families spread overtwo labels with 12 parameters, where 30 percent of family data is used as training data, and 70 percent of family data becomes as test data. The test results show that the average accuracy of the Naïve Bayes calcification method is 82.68%, while the K- Nearest Neighbor classification method is 85.57%. This study concludes that the best method for classifying low- income families is the Naïve Bayes method]]>
Copyrights © 2021
