Title :
Comparing NARX and NARMAX models using ANN and SVM for cash demand forecasting for ATM
Author :
Acuña, Gonzalo ; Ramirez, Cristián ; Curilem, Millaray
Author_Institution :
Dept. de Ing. Inf., Univ. de Santiago de Chile, Santiago, Chile
Abstract :
A comparative study between NARMAX and NARX models developed with ANN and SVM when used to forecast cash demand for ATMs is conducted. A simple methodology for developing SVM-NARMAX models is proposed. The best results were obtained with NARX-ANN models. In addition no significant differences were found between NARX and NARMAX for both ANN and SVM. Hence it seems advisable to choose simpler models, such as NARX and a user-friendly tool like ANN at least for this particular application.
Keywords :
automatic teller machines; autoregressive moving average processes; forecasting theory; neural nets; support vector machines; ATM; NARX-ANN model; SVM-NARMAX model; artificial neural networks; automatic teller machines; cash demand forecasting; nonlinear autoregressive moving average model; nonlinear autoregressive with exogenous variables; support vector machine; user friendly tool; Artificial neural networks; Autoregressive processes; Mathematical model; Online banking; Predictive models; Support vector machines; Training; ANN; ATM; NARMAX; NARX; SVM; forecasting;
Conference_Titel :
Neural Networks (IJCNN), The 2012 International Joint Conference on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1488-6
Electronic_ISBN :
2161-4393
DOI :
10.1109/IJCNN.2012.6252476
