K-Means Clustering Method to Make Credit Payment Groupinhg Efficient

Credit payment management is one of the main challenges in the financial sector, especially in grouping customers based on risk and payment patterns. This study aims to evaluate the K-Means Clustering method in improving the efficiency of credit payment data clustering. The dataset used includes information on payment history, loan amount, tenor, and credit status from financial institutions. The research approach involves data processing stages, application of the K-Means algorithm, and evaluation of results using the Davies-Bouldin Index and Silhouette Score metrics. The results of the analysis show that the K-Means method is effective in identifying customer payment patterns and dividing them into three main clusters: high, medium, and low risk. In addition, this study found that determining the optimal number of clusters using the Elbow Method can improve the accuracy of the clustering results. The resulting model makes a significant contribution to credit risk management, helping financial institutions make strategic decisions related to credit policies and risk mitigation. This study offers practical implications, including increased operational efficiency and predictive ability against potential bad debts. Further studies are recommended to integrate this method with other algorithms to improve the performance of large-scale data analysis.