Optimizing the deposit portfolio of a private bank

In this study based on the historical statistics of deposits of a private bank in four different categories , the purpose is to estimate the optimal share of the bank's quadrilateral deposits with the aim of minimizing the interest paid on these deposits and observing the limit of the bank's deposit matrix within the framework of the bank's upstream documents. To solve this optimization, optimization algorithms in Matlab Package have been used due to the nonlinear objective function. Initially, the results and data prediction for each of the bank deposits are based on previous data and using machine learning and regression methods in the relevant section. Then, by constructing the objective function and constraints and inserting the bank deposit and deposit data, the optimal deposit share is extracted using the internal point method. The results show that long-term stable sensitive deposit with expensive and then unstable current deposit sensitive to cheap business have the largest share in total bank deposits, which should be considered in the planning of bank deposits.