An ann and ga approach for demand forecasting and routing for cash management

Forecasting of cash demand and cash transportation are critical processes for all bank asynchronous transfer modes (ATMs). In this paper, an application is presented to accurate forecasting of cash demand and minimizing the transportation cost. In the first step of the proposed application, artificial neural network is implemented for forecasting the amount of withdrawn and deposited money from an ATM in one day. Hence, a more accurate way is provided to determine the amount of money that will be loaded into the ATM, and opportunity costs are minimized. Then, we applied genetic algorithm for minimizing the transportation cost of cash deposit to the ATMs.