<![CDATA[The development of information technology and artificial intelligence has brought significant changes to the Islamic microfinance industry. Baitul Maal wat Tamwil (BMT) faces challenges in managing and analyzing increasingly complex customer data. This study aims to optimize customer data prediction at BMT Al-Hikmah Permata using the Random Forest algorithm with pruning techniques. The methodology includes customer data collection from 2021 to 2024, data pre-processing, modeling using Random Forest with and without pruning, and model evaluation. Results show that applying pruning techniques significantly improves model performance, with increases of 3.9% in accuracy, 5% in precision, 3.9% in recall, and 4.5% in F1-score. Model complexity is also reduced, with an 81% decrease in node count and a 59% reduction in tree depth. In conclusion, pruning techniques prove effective in enhancing prediction accuracy and efficiency of the Random Forest model for BMT customer data analysis, which can support better decision-making in Islamic microfinance services]]>
Copyrights © 2024
