<![CDATA[BPS routinely conducts censuses and surveys involving BPS partners in data collection and processing. Ensuring these partners exhibit good performance is crucial to minimize the risk of moral hazard, which can negatively impact stakeholders. This research aims to implement machine learning into an information system to recommend statistical partners based on classification results. The best model identified is XGBoost, which is integrated into the system for generating recommendations. System testing using black-box methods confirmed compliance in 41 scenarios. Additionally, the System Usability Scale (SUS) questionnaire yielded an average score of 65.5, indicating the system's potential and suitability for further development. The findings offer insights into utilizing partner characteristics data and evaluation in BPS's censuses and surveys, particularly for selecting assigned partners.]]>
Copyrights © 2024
