Family Hope Program Recipient Determination System Using The Naive Bayes Method

Abstract

Poverty is still a problem that Indonesian people continue to face. To achieve prosperity and social justice for all Indonesian citizens, poverty can be considered a situation where a person does not have the ability to fulfill their basic needs, such as food, shelter, clothing, has a low income, has limited access to education, and has work skills. which is inadequate. The government, as a policy maker, has made various efforts to reduce poverty, one of which is through the Family Hope Program (PKH). However, in its implementation, the distribution of PKH assistance still faces problems in terms of targeting accuracy. To overcome this problem, a system is needed that can provide recommendations about who is worthy of receiving PKH assistance. One approach that can be used is a decision support system (DSS) using the Naïve Bayes method. Naïve Bayes is an algorithm used for text classification and is a Machine Learning method that focuses on calculating probability and statistics to predict future probabilities based on past experience. With the help of SPK, this system is able to provide recommendations about who should receive assistance. PKH is based on criteria such as school children, toddlers, pregnant women, the elderly and people with disabilities. Test results using the Naïve Bayes method with Confusion Matrix calculations show an accuracy level of 75%. Next, a comparison was carried out with testing using Cross Validation, which showed an increase in accuracy compared to previous testing without using 10-fold Cross Validation.