<![CDATA[Credit restructuring remains essential to banking risk management because unsuccessful restructuring may lead to further deterioration in credit quality, particularly among rural banks with limited analytical capabilities. This study aimed to identify the factors associated with successful loan restructuring, develop a predictive model, and formulate data-driven strategies for PT BPR Jabar Perseroda. A quantitative business analytics approach was employed using the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework. Historical data consisting of 1,200 loan restructuring observations from January to December 2025 were analyzed through descriptive, predictive, and prescriptive analytics using RapidMiner. Three classification algorithms—Random Forest, Gradient Boosted Tree, and Decision Stump—were evaluated based on accuracy, precision, recall, and F1-score. The findings showed that Random Forest achieved the best predictive performance, with an accuracy of 96.67%, precision of 98.65%, and recall of 96.05%. Initial collectibility status was the factor most strongly associated with restructuring success, followed by collateral type and the number of arrears, whereas the debt-to-income ratio and economic sector showed relatively weaker relationships. These findings supported the implementation of risk-based debtor segmentation, appropriate restructuring schemes, intensive post-restructuring monitoring, and the development of an early warning system. The study concluded that the integration of business analytics and machine learning could improve loan restructuring decision-making; however, predictive results should complement rather than replace professional judgment and prudent banking governance practices.]]>
Copyrights © 2026
