Choosing the Appropriate Branch for Participation Banks Through Machine Learning

摘要

The size of a bank is directly proportional to the number of branches it has. In the traditional banking system, banks try to reach more customers by opening new branches. Each new branch to be opened carries a cost for the bank. Therefore, a feasibility study is required for the new branch planned to be opened. While conducting feasibility studies, demographic information is generally used and it is aimed to open the branch in a place that will provide maximum efficiency. For this purpose, in the first phase of this study, the branch to be opened by a newly established participation bank was found through machine learning. Location data of other participation bank branches that have been in service for many years were used as datasets. With the OPTICS algorithm, a clustering structure was created with at least one kilometer and at least three branches. In the second phase of the study, the priority of the branches decided to open was found through analytical work. In the analytical study, development indices and levels of the cities were used.