A Data Mining Approach to Enhancing Birth and Death Registration Processes

Erfan, Hasmin (2025) A Data Mining Approach to Enhancing Birth and Death Registration Processes. Doctoral thesis, Asia e University.

	Text Thesis Erfan Hasmin.pdf Restricted to Repository staff only Download (4MB)
	Text Thesis Erfan Hasmin-1-24.pdf Download (314kB)

Abstract

Accurate and timely birth and death registration is crucial for effective policymaking and public service delivery. However, Indonesia’s current population administration system faces challenges such as centralized registration processes and low public awareness, leading to delays and incomplete records. This study explores the use of data mining techniques to enhance registration efficiency by analyzing birth and death records from Makassar city’s population and civil registration office. Using k-means clustering, apriori association rules, and c5 decision trees, this research identifies key patterns influencing late registrations. The optimal number of clusters of clusters for birth and death data is determined as three using elbow and silhouette validation methods. The apriori algorithm refines registration data by identifying associations that reduce inconsistencies, while decision three analysis highlights critical factors contributing to registrations delays. a total 45 decision trees were generated, leading to policy recommendation aimed at improving data collection and public compliance. This study contributes to ICT governance and public administration by demonstrating how data-driven approaches can optimize civil registration service. The findings offer actionable insights for policymakers to enhance registration models, reduce delays, and improve public accessibility. Future research may explorer the integration of deep learning models for further automate the registration process and enhance predictive accuracy.

Item Type:	Thesis (Doctoral)
Uncontrolled Keywords:	Civil registration, data mining model, k-means, apriori, c5.0
Divisions:	School of Graduate Studies
Depositing User:	Siti Nor Fairuz Rosaidee
Date Deposited:	14 Jan 2026 02:04
Last Modified:	14 Jan 2026 02:04
URI:	http://ur.aeu.edu.my/id/eprint/1415

Actions (login required)

View Item