ATM Supply Scheduling Optimization: Demand Prediction to Intelligent Route Planning

Nowadays Automated Teller Machines (ATMs) are one of the main cash circulation sources in societies. Banks and their clients depend heavily on their availability and their ability to consistently serve client requests. In order to achieve that high availability, banks are trying to optimize their ATM resupply planning in order to ensure client satisfaction while minimizing their own costs and the amount of capital that is idle inside the ATMs. The solution proposed in this paper is trying to find the most fitting algorithms in order to predict the optimal time that an ATM should be resupplied using machine learning techniques. The algorithms take into consideration historical data and external data that may affect the resupply process or the client activity per ATM, such as holidays or street events near the ATM. The results are being used by a route optimization algorithm in order to find the optimal supply planning, minimizing costs and energy consumption.