Hybrid Decision Tree Method and C4.5 Algorithm for a Recommendation System in Determining Recipients of Direct Cash Assistance (BLT)

Abstract

Development of a recommendation system to determine recipients of Direct Cash Assistance (BLT) using the C4.5 algorithm hybrid method and decision tree. In the current era of digitalization, the BLT program is a solution for the Indonesian government to help people affected by the COVID-19 pandemic. In this study, we propose a recommendation system that combines the C4.5 algorithm and a decision tree to increase accuracy and efficiency in determining BLT beneficiaries. Primary data was obtained through interviews and observations, while secondary data was obtained from the village administration, written reports, journals, theses and previous research. The results showed that the C4.5 algorithm and decision tree hybrid method gave good performance in determining BLT recipients. The C4.5 algorithm is used to calculate the accuracy of the training data and testing data with a ratio of 80% : 20%, while the decision tree is used to create a decision tree that classifies prospective BLT recipients. This research fills in the previous research gap regarding the recommendation system for determining BLT beneficiaries. The results of this study are expected to provide useful information for the government in making decisions regarding the BLT program, especially at the village or sub-district level. With an accurate and efficient recommendation system, financial assistance can be provided to those who really need it, helping to meet the basic daily needs of affected communities.