Machine Learning Comparison for Housing Rehabilitation Beneficiary Selection in Surabaya

Christy, Cathrine Abigael and Budianti, Luluk Harida and Prasetyo, Daniel Hary and Siswantoro, Joko (2026) Machine Learning Comparison for Housing Rehabilitation Beneficiary Selection in Surabaya. Journal of Information Technology and Computer Science, 11 (2). pp. 212-223. ISSN 2540-9824

PDF ID+908+(2).pdf - Published Version Download (499kB)

Abstract

The Surabaya City Government launched the ‘Dandan Omah’ Social Rehabilitation Program for Uninhabitable Houses (RTLH) in 2022. However, beneficiary selection during 2022–2024 period was conducted manually, leading to potentially subjective and less targeted decisions. This applied research established a data-driven support approach by executing structured procedure: constructing a preprocessing pipeline for a dataset of 1700 records with 11 features, implementing four supervised machine learning models (DT, RF, SVM, KNN), performing 10-fold cross-validation, and also hyperparameter tuning with 10-fold cross-validation across 2, 4, and 5 classification tasks. RF consistently achieved the best performance across all scenarios, while SVM demonstrated competitive baseline performance. After tuning, DT surpassed SVM on 5-class tasks and matched RF on 2-class tasks, making optimized DT a viable, interpretable alternative when decision accountability was essential. KNN consistently underperformed due to the curse of dimensionality. Overall performance declined as classification complexity increased, attributed to variability in field assessment standards. These findings suggested that RF and optimized DT could support more standardized and objective RTLH beneficiary selection. Future studies is recommended to identify influential input features to optimize model performance while maintaining explainability. Re-standardizing field assessment protocols is also recommended to improve data quality.

Item Type:	Article
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Engineering > Department of Informatic
Depositing User:	CATHRINE ABIGAEL CHRISTY
Date Deposited:	11 Sep 2026 07:44
Last Modified:	11 Sep 2026 07:44
URI:	http://repository.ubaya.ac.id/id/eprint/51265

Actions (login required)

View Item