Application of Data Mining Algorithms to Determine Priority Schools for the Free Nutritious Meal Program Based on Social Indicators in Pinrang Regency

Anas Nurdin Hadi; Jabaluddin Hamud; Siti Rahmah Sindar; Ahmad Husain; Azwar H.

doi:10.31764/jtam.v10i4.40194

Application of Data Mining Algorithms to Determine Priority Schools for the Free Nutritious Meal Program Based on Social Indicators in Pinrang Regency

Anas Nurdin Hadi, Jabaluddin Hamud, Siti Rahmah Sindar, Ahmad Husain, Azwar H.

Abstract

This study aims to determine priority schools for the Free Nutritious Meal Program in Pinrang Regency based on students’ social indicators using a data mining approach. The implementation of educational assistance programs requires objective and data-driven decision-making to ensure that support is distributed to schools with the highest level of social vulnerability. Therefore, this research applies the K-Means Clustering algorithm to classify schools according to the socioeconomic conditions of their students. The research employed a quantitative approach involving 593 students from 10 senior high schools and vocational schools in Pinrang Regency. The dataset was collected using questionnaires and school administrative records. Students were evaluated using multidimensional socioeconomic indicators representing household economic conditions, educational background, housing characteristics, family dependency, transportation accessibility, and social assistance status. Each indicator was transformed into a numerical score ranging from 1 to 4 to quantify the level of socioeconomic vulnerability. The clustering process was conducted using the K-Means Clustering algorithm, while the optimal number of clusters was determined using the Silhouette Method. The results showed that the optimal clustering structure consisted of four clusters with a silhouette score of 0.234. Cluster 1 represented the highly prioritized group with the highest socioeconomic vulnerability, while Cluster 4 represented the priority group, Cluster 3 represented the moderately prioritized group, and Cluster 2 represented the non-priority group. The analysis indicated that School B and School H were categorized as highly prioritized schools because most of their students belonged to Cluster 1. Meanwhile, School G was categorized as a priority school, and School D was classified as moderately prioritized. The findings demonstrate that the K-Means Clustering method can effectively support educational policy decision-making by identifying school priority categories based on multidimensional social indicators. The novelty of this study lies in the development of a data-driven school prioritization framework that integrates ten multidimensional socioeconomic indicators into a K-Means Clustering model. Unlike the current prioritization approach, which primarily considers general vulnerability criteria and regional classification, the proposed framework quantitatively evaluates students' socioeconomic conditions to support a more objective, transparent, and evidence-based prioritization of schools for the Free Nutritious Meal Program.

Keywords

Data Mining; K-Means Clustering; Social Indicators; Silhoute Method; Priority School.

Full Text:

DOWNLOAD [PDF]

References

Al Aldowah, H., Al-Samarraie, H., & Fauzy, W. M. (2019). Educational data mining and learning analytics for 21st century higher education: A review and synthesis. Telematics and Informatics, 37, 13–49. https://doi.org/10.1016/j.tele.2019.01.007

Ajtai, I., Ștefănie, H., Costache, R., Mihai, B., Bui, D. T., & Baciu, C. (2023). Mapping social vulnerability to floods: A comprehensive framework using a vulnerability index approach and PCA analysis. Ecological Indicators.

Alqahtani, A., Rajkhan, A., & Aligery, A. (2022). Social vulnerability analysis using clustering techniques for educational assistance programs. IEEE Access, 10, 45621–45633. https://doi.org/10.1109/ACCESS.2022.3167428

Atif, M., Shafiq, M., Farooq, M., Ayub, G., Leisch, F., & Ilyas, M. (2023). Monitoring changes in clustering solutions: A review of models and applications. Journal of Probability and Statistics, 2023, 7493623. https://doi.org/10.1155/2023/7493623

Barnabas, B., Bavorova, M., & Madaki, M. Y. (2024). The effect of school feeding program on pupils' enrolment, attendance and performance in Northeastern Region of Nigeria. SAGE Open, 14(4). https://doi.org/10.1177/21582440241255809

Bittencourt, J. C. N., Costa, D. G., Portugal, P., & Vasques, F. (2024). A data-driven clustering approach for assessing spatiotemporal vulnerability to urban emergencies. Sustainable Cities and Society, 108, 105477. https://doi.org/10.1016/j.scs.2024.105477

Chaudhry, M., Shafi, I., Mahnoor, M., Vargas, D. L. R., Thompson, E. B., & Ashraf, I. (2023). A systematic literature review on identifying patterns using unsupervised clustering algorithms: A data mining perspective. Symmetry, 15(9), 1679. https://doi.org/10.3390/sym15091679

Fitzgerald, A., Avirmed, T., & Battulga, N. (2024). Exploring the factors informing educational inequality in higher education: A systematic literature review. International Journal of Inclusive Education. https://doi.org/10.1080/13603108.2024.2381121

Follett, L., & Henderson, H. (2023). A hybrid approach to targeting social assistance. Journal of Development Economics, 160, 103002. https://doi.org/10.1016/j.jdeveco.2022.103002

Hossin, M. A., Du, J., Mu, L., & Asante, I. O. (2023). Big data-driven public policy decisions: Transformation toward smart governance. SAGE Open, 13(4). https://doi.org/10.1177/21582440231215123

Kaur, A., Kumar, Y., & Sidhu, J. (2024). Exploring meta-heuristics for partitional clustering: Methods, metrics, datasets, and challenges. Artificial Intelligence Review, 57, 287. https://doi.org/10.1007/s10462-024-10920-1

Liu, T., Yu, H., & Blair, R. H. (2022). Stability estimation for unsupervised clustering: A review. WIREs Computational Statistics, 14(6), e1575. https://doi.org/10.1002/wics.1575

Lu, Y., Yeom, S., Maktoubian, J., Rahman, M. M., & Kim, S.-H. (2025). Improve Student Risk Prediction with Clustering Techniques: A Systematic Review in Education Data Mining. Education Sciences, 15(12), 1695. https://doi.org/10.3390/educsci15121695

Mah, J. C., Penwarden, J. L., Pott, H., Theou, O., & Andrew, M. K. (2023). Social vulnerability indices: A scoping review. BMC Public Health, 23(1), 1–11. https://doi.org/10.1186/s12889-023-16097-6

Majumder, S., Roy, S., Bose, A., & Roy Chowdhury, I. (2023). Multiscale GIS based-model to assess urban social vulnerability and associated risk: Evidence from 146 urban centers of Eastern India. Sustainable Cities and Society, 96, 104692. https://doi.org/10.1016/j.scs.2023.104692

Nasution, M. I., Siregar, B., & Harahap, M. K. (2024). Clustering analysis for social assistance recipient classification in educational institutions. Heliyon, 10(5), e24015. https://doi.org/10.1016/j.heliyon.2024.e24015

Palermos, D., Pavi, E., Halvatsiotis, P., Mangoulia, P., Sergentanis, T. N., & Psaltopoulou, T. (2024). Individual-based socioeconomic vulnerability and deprivation indices: A scoping review. Frontiers in Public Health, 12, 1403723. https://doi.org/10.3389/fpubh.2024.1403723

Putra, A. R., & Kurniawan, D. (2023). Data-driven educational assistance prioritization using clustering methods. Sustainability, 15(4), 3567. https://doi.org/10.3390/su15043567

Rahman, M. M., Islam, M. A., & Hossain, M. S. (2020). K-means clustering approach for student performance analysis and prediction. International Journal of Advanced Computer Science and Applications, 11(6), 493–499. https://doi.org/10.14569/IJACSA.2020.0110662

Rokach, L., & Maimon, O. (2020). Data mining with decision trees: Theory and applications (3rd ed.). World Scientific.

Romero, C., & Ventura, S. (2020). Educational data mining and learning analytics: An updated survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(3). https://doi.org/10.1002/widm.1355

Rousseeuw, P. J. (1987). Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53–65. https://doi.org/10.1016/0377-0427(87)90125-7

Sharma, A., & Sharma, S. (2021). Applications of clustering techniques in educational data mining: A systematic review. Journal of Big Data, 8(1), 1–28. https://doi.org/10.1186/s40537-021-00442-3

Singh, S., Kumar, S., & Sharma, R. (2023). Big data analytics and e-governance: Actors, opportunities, tensions, and applications. Technological Forecasting and Social Change, 193, 122612. https://doi.org/10.1016/j.techfore.2023.122612

Tan, C. Y. (2024). Socioeconomic status and student learning: Insights from an umbrella review. Educational Psychology Review, 36, Article 100. https://doi.org/10.1007/s10648-024-09929-3

Wang, D., Shinde, S., Young, T., & Fawzi, W. W. (2021). Impacts of school feeding on educational and health outcomes of school-age children and adolescents in low- and middle-income countries: A systematic review and meta-analysis. Journal of Global Health, 11, 04051. https://doi.org/10.7189/jogh.11.04051

Wani, A. A. (2024). Comprehensive analysis of clustering algorithms: Exploring limitations and innovative solutions. PeerJ Computer Science, 10, e2286. https://doi.org/10.7717/peerj-cs.2286

Zhang, L., Clay, O. J., Lee, S.-Y., & Howell, C. R. (2024). Analyzing Multiple Social Determinants of Health Using Different Clustering Methods. International Journal of Environmental Research and Public Health, 21(2), 145. https://doi.org/10.3390/ijerph21020145

DOI: https://doi.org/10.31764/jtam.v10i4.40194