Credit Risk Analysis at Baitul Tanwil Muhammadiyah Cooperative using Supervised Learning Algorithms

Credit default is a major challenge faced by microfinance institutions, including Koperasi Baitul Tanwil Muhammadiyah (BTM). The conventional credit scoring process, which relies on manual assessment, often leads to bias and inefficiency. This study aims to develop a credit risk analysis model using supervised learning algorithms to improve the accuracy of credit default prediction among cooperative members. The methodology includes data collection, preprocessing, data splitting into training and testing sets, model training, and performance evaluation using accuracy, precision, recall, F1-score, and AUCROC metrics. Four algorithms are employed: Logistic Regression, Decision Tree, Random Forest, and XGBoost. The expected outcome is a predictive model capable of supporting cooperative decision-making in credit approval through an objective and data-driven approach.

Keywords: Credit Risk, Cooperative, Supervised Learning, Machine Learning, BTM