Classification of Family Hope Program Assistance Recipients Using the C4.5 Algorithm with Z-Score Normalization (Case Study in Atu Lintang District)

One of the challenges in distributing social assistance is determining recipients who are truly eligible objectively and efficiently. This study develops a classification system for Family Hope Program (PKH) recipients by utilizing the C4.5 algorithm combined with Z-Score normalization to group citizen data into Eligible or Ineligible categories. The data used came from 551 residents of Atu Lintang District and included attributes such as house status, wall type, toilet facilities, occupation, and income. The research stages started from data preprocessing, attribute normalization, training the model, to evaluating its performance through metric such as accuracy, precision, recall, and F1-score. The evaluation results showed that the model achieved an accuracy of 94%, precision 0.96, recall 0.90, and F1-score 0.93 for the Eligible category. Based on the confusion matrix, the model was able to correctly classify 47 Eligible residents and 57 Ineligible residents. Analysis of the attributes showed that occupation was the most influential feature in the classification process. These results prove that the application of the C4.5 algorithm can be applied effectively to build a decision support system in the distribution of social assistance, and provide accurate and easy-to-understand results. This study also opens up opportunities for improving model performance by adding more data and testing with alternative algorithms going forward.