Clustered Support Vector Machine for ATM Cash Repository Prediction

Prediction of ATM cash repository in an optimal way is a crucial task. This paper deals with the application of cash prediction of NN5 time series data using support vector machines. The main objective of this paper is time series prediction of NN5 data along with and without clustering at rst stage, support vector regression (SVR) is applied on NN5 data and root mean square error is computed. Further, the same study was conducted by clustering ATMs using hierarchical clustering technique on NN5 data before applying SVR. Discrete time wrapping is used as a distance measure for clustering. Root mean square error has been calculated for such clustered group of ATMs and the average is calculated. Root Mean Square error indicates applications of clustering before applying Neural Network. It is shown to increases precision in forecasting of ATM Cash Repository