Implementation of Machine Learning Using Decision Tree Method for Social Assistance Recipient Classification

Aug 5, 2026

Distribution of social assistance in Indonesia faces persistent targeting errors, where financially able individuals may receive aid while truly eligible households are excluded. This study develops an interpretable machine learning classification model for Bojonggenteng Village using the C4.5 decision tree algorithm, selected for strong performance on categorical data. The workflow includes problem definition, literature review, data collection, preprocessing, model training, and evaluation. Using 904 records from 2023 BPNT and PBI-JK programs in RapidMiner, results show 98.90% accuracy, 100% precision, 97.60% recall, and AUC 0.988, supporting fair, data-driven decisions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Introduction

Background of Social Assistance Targeting Problems

Decision Tree and C4.5 Approach

Research Objective and Method Goal

Implementation of Machine Learning Using Decision Tree Method for Social Assistance Recipient Classification Akbar Ilham Perhan1)*, Indra Yustiana2), Imam Sanjaya3) 1)2)3) Informatics Engineering, Faculty of Engineering, Computer and Design, Nusa Putra University, Sukabumi, Indonesia 1)[akbar.perhan_ti21@nusaputra.ac.id](akbar.perhan_ti21@nusaputra.ac.id) 2)[indra.yustiana@nusaputra.ac.id](indra.yustiana@nusaputra.ac.id) 3)[imam.sanjaya@nusaputra.ac.id](imam.sanjaya@nusaputra.ac.id) Article history: Received 30 June 2025; Revised 02 July 2025; Accepted 10 July 2025; Available online 10 August 2025 Keywords: Classification Decision Tree C4 .5 Machine Learning RapidMiner Social Assistance Abstract The distribution of social assistance in Indonesia often faces challenges inaccuracy, where individuals who are financially capable still receive aid, while those truly in need are excluded. To address this issue, this study applies a Machine Learning approach using the C4.5 Decision Tree algorithm to classify the eligibility of recipients in Bojonggenteng Village. This algorithm was chosen because it is easy to interpret, performs well, and is suitable for categorical data. The main objective of the study is to develop a classification model that enhances the objectivity and accuracy in determining aid recipients, ensuring that assistance is directed to those who truly need it. The research process involves several stages, including problem identification, literature review, data collection, preprocessing, classification, and model evaluation. A total of 904 records from the 2023 BPNT and PBI-JK programs were obtained in collaboration with the local village authorities. The classification process was conducted using RapidMiner, which allows for visual data processing and model building without requiring programming. The model evaluation was carried out using a confusion matrix, yielding an accuracy of 98.90%, precision of 100%, recall of 97.60%, and an AUC score of 0.988. These results indicate that the C4.5 algorithm is effective for prediction tasks and can be a valuable tool in supporting fair and data-driven decision-making in social assistance programs. This study concludes that the application of Machine Learning in this context improves the fairness and transparency of aid distribution and recommends future research to involve larger datasets for broader implementation. I. INTRODUCTION Social Assistance is one of many programs designed by the government to combat poverty and improve the standard of living of the population [1] . This program is made to improve people's lives [2] and designed to ensure that aid reaches the groups in society who truly need it, thereby significantly improving their quality of life [3] . However, in its implementation, the process of determining eligibility for social assistance still faces various challenges [4], particularly in terms of accuracy and objectivity. Various public criticisms directed at the government indicate that the distribution of assistance in Indonesia is still not entirely well-targeted. There have been cases where economically capable families received aid [5], while poor families were not registered as beneficiaries. This phenomenon can also be found in various regions, including Bojonggenteng Village. Bojonggenteng Village was chosen as the research location because in this area there are still various problems related to the accuracy of social assistance distribution, such as a mismatch between aid recipients and actual economic conditions. In addition, the socio-economic conditions of the Bojonggenteng community, which are quite diverse, provide their own challenges in the process of classifying recipients of targeted assistance. This diversity is an important factor in testing the effectiveness of the classification model developed. Easy access to data and good cooperation from the village are also strong reasons why researchers chose Bo

FAQs

Why does social assistance targeting in Indonesia need improvement?

It still faces accuracy and objectivity issues, including cases where capable families receive aid and poor families are not registered as beneficiaries.

How does the study classify social assistance recipients?

It applies the C4.5 decision tree algorithm to build a classification model for recipient eligibility in Bojonggenteng Village.

What evaluation metrics were used and what were the results?

The study uses a confusion matrix, achieving 98.90% accuracy, 100% precision, 97.60% recall, and an AUC score of 0.988.

Aug 5, 2026

Upload by Seraphina