Advertisement

The Improvement of Forecasting ATMs Cash Demand of Iran Banking Network Using Convolutional Neural Network

  • Soodabeh Poorzaker Arabani
  • Hosein Ebrahimpour Komleh
Research Article - Computer Engineering and Computer Science
  • 7 Downloads

Abstract

One of the problems related to the banking system is Automated Teller Machine (ATM) cash demand forecasting. If an ATM faces a shortage of cash, it will face the decline of bank popularity and in turn will have some costs and the bank will encounter decreasing customers use of these systems. On the other hand, if the bank faces cash trapping at an ATM, regarding inflation in Iran, cash trapping and the lack of using it will have a negative impact on bank profitability. The aim of this study is to predict accurately to eliminate the posed double costs. Since the information related to the amount of cash is daily, each ATM will have a behavior as time series and also because the aim of this study is to predict the demand for cash from the 1056 ATMs, we are facing data from the type of panel. The methods that are used for forecasting ATM cash demand in this research include: forecasting by statistical method, artificial neural network intelligent method, Support vector machine and Convolutional neural network. We will compare the results of these methods and show that intelligent methods in comparison with statistical analysis have higher accuracy.

Keywords

Artificial neural network ATM cash demand Intelligent forecasting Statistical forecasting Convolutional neural network Support vector machine 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jadwal, P.K.; Jain, S.; Gupta, U.; Khanna, P.: K-means clustering with neural networks for ATM cash repository prediction. In: International Conference on Information and Communication Technology for Intelligent Systems. pp. 588–596. (2017)Google Scholar
  2. 2.
    Venkatesh, K.; Ravi, V.; Prinzie, A.; Van den Poel, D.: Cash demand forecasting in ATMs by clustering and neural networks. Eur. J. Oper. Res. 232, 383–392 (2014)CrossRefGoogle Scholar
  3. 3.
    Simutis, R.; Delijonas, D.; Bastina, L.; Friman, J.; Drobinov, P.: Optimization of cash management for ATM network. Inf. Technol. Control. 36, 117–121 (2007)Google Scholar
  4. 4.
    Catal, C.; Fenerci, A.; Ozdemir, B.; Gulmez, O.: Improvement of demand forecasting models with special days. Proc. Comput. Sci. 59, 262–267 (2015)CrossRefGoogle Scholar
  5. 5.
    Simutis, R.; Dilijonas, D.; Bastina, L.: Cash demand forecasting for ATM using neural networks and support vector regression algorithms. In: 20th International Conference, EURO Mini Conference, “Continuous Optimization and Knowledge-Based Technologies” (EurOPT-2008), Selected Papers, Vilnius. pp. 416–421. (2008)Google Scholar
  6. 6.
    Ramírez, C.; Acuña, G.: Forecasting cash demand in ATM using neural networks and least square support vector machine. In: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. pp. 515–522. (2011)CrossRefGoogle Scholar
  7. 7.
    Garcia Pedrero, A.; Gomez Gil, P.: Time series forecasting using recurrent neural networks and wavelet reconstructed signals. In: 20th International Conference on Electronics, Communications and Computer (CONIELECOMP), pp. 169–173. (2010)Google Scholar
  8. 8.
    Darwish, S.M.: A methodology to improve cash demand forecasting for ATM network. Int. J. Comput. Electr. Eng. 5, 405 (2013)CrossRefGoogle Scholar
  9. 9.
    Zandevakili, M.; Javanmard, M.: Using fuzzy logic (type II) in the intelligent ATMs’ cash management. Int. Res. J. Appl. Basic Sci. 8, 1516–1519 (2014)Google Scholar
  10. 10.
    Borda, P.; Levajkovic, T.; Kresoja, M.; Marceta, M.; Mena, H.; Nikolic, M.; Stojancevic, T.: Optimization of ATM filling-in with cash. 99th European study group with industry, pp. 1–16 (2014)Google Scholar
  11. 11.
    Dandekar, P.V.; Ranade, K.M.: ATM cash flow management. Int. J. Innov. Manag. Technol. 6, 343 (2015)CrossRefGoogle Scholar
  12. 12.
    Andrawis, R.R.; Atiya, A.F.; El-Shishiny, H.: Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition. Int. J. Forecast. 27, 672–688 (2011)CrossRefGoogle Scholar
  13. 13.
    Aseev, M.; Nemeshaev, S.; Nesterov, A.: Forecasting cash withdrawals in the ATM network using a combined model based on the holt-winters and markov chains. Int. J. Appl. Eng. Res. 11, 7577–7582 (2016)Google Scholar
  14. 14.
    Brooks, C.: Introductory Econometrics for Finance, pp. 487–509. Cambridge University Press (2014)Google Scholar
  15. 15.
    Palit, A.K.; Povovic, D.: Computational Intelligence in Time Series Forecasting, pp. 129–130. Springer (2005)Google Scholar
  16. 16.
    Theodoridis, S.; Koutroumbas, K.: Pattern Recognition, pp.151–196. Elsevier (1999)Google Scholar
  17. 17.
    Goodfellow, I.; Bengio, B.: Gurville A.: Deep Learning. MIT Press, Cambridge (2016)zbMATHGoogle Scholar
  18. 18.
    Anandhi, V.; Manicka Chezian, R.: Support vector regression in forecasting. Int. J. Adv. Res. Comput. Commun. Eng. 2(10), 4148–4151 (2013)Google Scholar
  19. 19.
    Siami Namini, S.; Siami Namini, A.: Forecasting Economics and Financial Time Series: ARIMA vs. LSTM. (2018). arXiv:1803.06386
  20. 20.
    Zheng, J.; Zhang, G.: Research on exchange rate forecasting based on deep belief network. Neural Comput. Appl. (2017).  https://doi.org/10.1007/s00521-017-3039-z

Copyright information

© King Fahd University of Petroleum & Minerals 2018

Authors and Affiliations

  • Soodabeh Poorzaker Arabani
    • 1
  • Hosein Ebrahimpour Komleh
    • 1
  1. 1.Department of EngineeringUniversity of KashanKashanIran

Personalised recommendations