International Journal of Enhanced Research in Science Technology & Engineering, ISSN: 2319-7463 Vol. 3 Issue 2, February-2014, pp: (318-326), Impact Factor: 1.252, Available online at: www.erpublications.com Page | 318 Approximating Methodology: Managing Cash in Automated Teller Machines using Fuzzy ARTMAP Network Nidhi Arora 1 , Jatinder Kumar R. Saini 2 1 M.C.A. Department, U.V. Patel College of Engineering, Ganpat University, Kherva, India 2 Narmada College of Computer Application, Bharuch, Gujarat, India Abstract: Determining an optimized amount of cash in bank’s Automatic Teller Machines (ATM) is a tricky job, as the demand for cash fluctuates due to change in customer’s behavior, preferences, seasonality, time etc. The decision of optimized cash refilling in ATM is done manually according to corporate policies and past experience. This process may sometimes lead to poor service or unnecessary cost due to under or over-estimation of cash demand. For this reason, finding the best match between cash requirement and demand fulfillment becomes a crucial decision for bank authorities. Therefore, the purpose for banks is to decide an optimum amount of money that should be placed in ATM to minimize opportunity costs and at the same time to satisfy the customers’ untimely and uncertain requirements. The paper suggests an application of fuzzy ARTMAP Network for proactively analyzing and forecasting daily cash requirement in ATM assuring prompt cash availability and dispensing service. Parameter selection is performed using neighborhood mutual information-based algorithm for attribute reduction to find best parameters. Simulation results for ATM cash forecasting show the feasibility and effectiveness of the proposed method. Keywords: Automated Teller Machine, Cash Management, Neighborhood Mutual Information Algorithm, Parameter Selection, Fuzzy ARTMAP Network, Forecasting. Introduction Automated Teller Machines (ATM) are becoming popular now-a-days among people and is of significant importance to the banking sector. The services offered by ATM help the bank in generating more revenue than early days. Formally defined, ATM is a programmed device, which provides a time-independent and easy-to-use method to customers of bank to perform financial transactions without having the intervention of bank staff. ATM machine was first introduced solely as a cash dispensing machine, but it can now perform other banking services such as cash withdrawals, funds transfers from one account to the other and payment of bills etc. [1]. These machines are connected to banks, providing all basic facilities to their customers like cash deposit and withdrawal, balance enquiry, printing mini-statement, fund transfer, cheque book request, mobile recharge, payment of utility bills etc. even after business hours and on holidays. Banks have experienced a growing need of services at ATM due to improvement in literacy level of customers. According to Moutinho [24], ATM facility has resulted in speed of transactions and has saved time of customers. ATM machines are preferred to banks which are crowded and sometimes take lot of time even for simple transactions due to long waiting queues. ATM technology’s customized service offerings provide a better alternative for simple banking, reduces waiting time for customers, serves as a channel for service delivery and provides vital information needed by customers in the shortest possible time [22]. Looking from the bank’s viewpoint, ATMs not only reduce the number of queued-up customers, reduce cost of hiring tellers, but also lend a hand in benefiting the society, government and ultimately to the economy of the country. Cash withdrawal is the most commonly used service at ATMs amongst all discussed above. Maintaining sufficient amount of cash round the clock in ATMs is difficult because sometimes extraneous cash is kept lying, while some other times customers needing cash have to go back without cash due to unavailability of required amount. This means that there is a buzzing need to approximately predict the cash demand at ATM which is indeed challenging. Some banks typically maintain as much as 40% more liquidity at their ATMs than what's needed, even though many experts consider cash excess of 15% to 20% to be sufficient. Through currency management optimization, banks can avoid falling into the trap of maintaining too much cash and begin to profit by mobilizing idle cash [28]. Maintaining excessive liquidity is uneconomical simply because the bank can invest it, while maintaining less liquidity can be disastrous as the ATM running out of cash gives dissatisfaction to customers. Hence, an adaptive optimal amount of cash should be maintained at bank ATMs. Stocking cash in ATM entails costs that can be broadly divided in two contributions: financial costs and operational costs [15]. The first are mainly due to unused stock rated by annual passive interests, while time to perform and supervise the task, maintenance, out-of-service and risk of robbery are associated to the second.