Comparison of Computational Intelligence Models on Forecasting Automated Teller Machine Cash Demands

Abstract

We take up the problem of forecasting the amount of money to be withdrawn from automated teller machines (ATM). We compare the performances of eleven different algorithms from four different research areas on two different datasets. The exploited algorithms are fuzzy time series, multiple linear regression, artificial neural network, autoregressive integrated moving average, gaussian process regression, support vector regression, long-short term memory, simultaneous perturbation stochastic approximation, migrating birds optimization, differential evolution, and particle swarm optimization. The first dataset is very volatile and is obtained from a Turkish bank whereas the more stationary second dataset is obtained from a UK bank which was used in competitions previously. We use mean absolute deviation (MAD) to compare the algorithms since it provides a universal comparison ability independent of the magnitude of the data. The results show that support vector regression (SVR) performs the best on both data sets with a very short run time.