Clustered Support Vector Machine for ATM Cash Repository Prediction

  • Pankaj Kumar JadwalEmail author
  • Sonal Jain
  • Umesh Gupta
  • Prashant Khanna
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 713)


Optimal prediction of cash in ATMs is a critical task. This research paper is concerned with the application of cash requirement forecasting of NN5 dataset by most promising machine learning technique support vector machine (SVM). Primary objective of this research paper is time series prediction of NN5 data with support vector regression at the first stage and further root mean square error (RMSE) is computed. Furthermore, the same study was conducted by clustering ATMs using k means clustering technique on NN5 data before applying support vector regression. Root mean square error (RMSE) is calculated for the clusters of ATMs, and average of RMSE retrieved from clusters is compared with accuracy obtained from single baseline SVM. RMSE indicates the application of unsupervised learning (clustering) used as a preprocessing step towards increases precision in the prediction of cash in ATMs.


Preprocessing Clustering Prediction Support vector machine 


  1. 1.
    Ojemakinde, B.T.: Support vector regression for non-stationary time series (2006)Google Scholar
  2. 2.
    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(3), 672–688 (2011)CrossRefGoogle Scholar
  3. 3.
    Wichard, J.D.: Forecasting the NN5 time series with hybrid models. Int. J. Forecast. 27(3), 700–707 (2011)CrossRefGoogle Scholar
  4. 4.
    Coyle, D., Prasad, G., McGinnity, T.M.: On utilizing self-organizing fuzzy neural networks for financial forecasts in the NN5 forecasting competition. In: Proceedings of the International Joint Conference on Neural Networks (2010)Google Scholar
  5. 5.
    Teddy, S.D., Ng, S.K.: Forecasting atm cash demands using a local learning model of cerebellar associative memory network. Int. J. Forecast. 27(3), 760–776 (2011)CrossRefGoogle Scholar
  6. 6.
    Ben Taieb, S., Bontempi, G., Atiya, A.F., Sorjamaa, A.: A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition. Expert Syst. Appl. 39(8), 7067–7083 (2012)CrossRefGoogle Scholar
  7. 7.
    Boyd, W.: Support vector machine for regression and applications to financial forecasting. IJCNN, IEEE (x), 6348 (2000)Google Scholar
  8. 8.
    Tay, F.E.H., Cao, L.J.: Improved financial time series forecasting by combining support vector machines with self-organizing feature map. Intel. Data Anal. 5, 339–354 (2001)CrossRefGoogle Scholar
  9. 9.
    Cao, L., Tay, F.E.H.: Modified support vector machines in financial time series forecasting. Neurocomputing 48(1–4), 847–861 (2002)zbMATHGoogle Scholar
  10. 10.
    Cao, L.J., Chua, K.S., Guan, L.K.: e-descending support vector machines for financial time series forecasting. Neural Process. Lett. 15, 179–195 (2002)Google Scholar
  11. 11.
    Van Gestel, T. et al.: Financial time series prediction using least squares support vector machines within the evidence framework. IEEE Trans. Neural Netw. 12(4), 809–821 (2001)CrossRefGoogle Scholar
  12. 12.
    Pai, P.-F., Lin, K.-P., Lin, C.-S., Chang, P.-T.: Time series forecasting by a seasonal support vector regression model. Expert Syst. Appl. 37(6) (2010)CrossRefGoogle Scholar
  13. 13.
    Hung, C., Hung, C., Lin, S.: Predicting Time series using integration of moving average and support vector regression. Int. J. Mach. Learn. Comput. 4(6), 491–495 (2014)CrossRefGoogle Scholar
  14. 14.
    Harris, T.: Credit scoring using the clustered support vector machine. Expert Syst. Appl. 42(2), 741–750 (2015)CrossRefGoogle Scholar
  15. 15.
    Khanarsa, P., Sinapiromsaran, K.: Multiple ARIMA subsequences aggregate time series model to forecast cash in ATM. In: 2017 9th International Conference on Knowledge and Smart Technology: Crunching Information of Everything, KST 2017, pp. 83–88 (2017)Google Scholar
  16. 16.
    Jadwal, P.K., Jain, S., Gupta, U., Khanna, P.: K-Means clustering with neural networks for ATM cash repository prediction. In: Satapathy, S., Joshi, A. (eds.), Information and Communication Technology for Intelligent Systems (ICTIS 2017), ICTIS 2017, vol. 1. Smart Innovation, Systems and Technologies, vol. 83. Springer, Cham (2018)Google Scholar
  17. 17.

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Pankaj Kumar Jadwal
    • 1
    Email author
  • Sonal Jain
    • 2
  • Umesh Gupta
    • 3
  • Prashant Khanna
    • 4
  1. 1.JK Lakshmipat UniversityJaipurIndia
  2. 2.Department of Computer Science EngineeringJK Lakshmipat UniversityJaipurIndia
  3. 3.Department of MathematicsJK Lakshmipat UniversityJaipurIndia
  4. 4.WintecHamiltonNew Zealand

Personalised recommendations