Financing-Limit Prediction Classifier in Islamic Bank Using Tree-Based Algorithms

Abstract

Islamic banks are one of the financial institutions that has been proven to be the catalyst to end extreme poverty in the world. However, amid the massive development of Industry 5.0, research about technology adaptation in Islamic banks is still considered rare. The aim of this study is to develop a technology that will help Islamic banks in making their financing decision more efficient. By using the current outstanding financing data in an Islamic bank, this study proposes a machine learning algorithm that could predict a financing limit based on customer classification. The tree-based learning algorithms used to build the algorithm have shown impressive results. The results show that the basic algorithm which is the Decision Tree gives 86% prediction accuracy. The algorithm is then improved by using the Random Forest algorithm. The Random Forest algorithm gives 91% prediction accuracy which significantly improves the base learning algorithm. Future research in this area is needed as the need to implement sophisticated technology is prominent in making Islamic banking more accessible across the globe.