ATM Cash Prediction Using Time Series Approach

Abstract

One of the main challenges in today's banking industry is to forecast the cash demand of their ATM network. Each ATM must be filled with the right amount so that neither a customer's transaction is rejected because of out-of-cash status, nor the idle cash ruins the opportunity for the bank to earn profit on it. This paper proposed a time-series model for forecasting the cash demands of each ATM in a network of ATMs for a specific financial institution. Using the transaction data of each ATM we build a Vector Auto Regressive Moving Average with Exogenous Variable model (VAR-MAX) for each ATM. We compared our proposed approach with one recently proposed Recurrent Neural Network (RNN) approach termed as Long-Short Term Memory(LSTM) which was reported to performed best for this problem. Our proposed model using the exogenous variable performed better than this model. The study used a dataset comprises of transaction of 7 ATMs from the period of June 2013 to December 2015 from some of the financially busy areas of Karachi Pakistan. The Symmetric Mean Absolute Percentage Error (SMAPE) is used to reports evaluation from the experiments.