Artificial Neural Network Application in Modelling Revenue Returns from Mobile Payment Services in Kenya
American Journal of Theoretical and Applied Statistics
Volume 3, Issue 3, May 2014, Pages: 60-64
Received: Mar. 28, 2014; Accepted: Apr. 25, 2014; Published: May 10, 2014
Views 3262      Downloads 171
Authors
Kyalo Richard, Jomo Kenyatta University Department of Statistics and Actuarial Science, Nairobi, Kenya
Waititu Anthony, Jomo Kenyatta University Department of Statistics and Actuarial Science, Nairobi, Kenya
Wanjoya Anthony, Jomo Kenyatta University Department of Statistics and Actuarial Science, Nairobi, Kenya
Article Tools
Follow on us
Abstract
Artificial Neural Networks has recently shown a great applicability in time-series analysis and forecasting thus correctly deducing the unseen part of the population even if the sample data contain noisy information. In this paper we used Neural Network to model revenue returns from mobile payment services using dataset extracted from Central Bank of Kenya website. The network with one or two hidden layers was tested with various combination of neurons, and results were compared in terms of forecasting error. It was observed that ANN if properly trained accurately forecast Revenue returns on mobile payments services in Kenya.
Keywords
Neural Network, Quasi Newton, Forecasting, Generalization
To cite this article
Kyalo Richard, Waititu Anthony, Wanjoya Anthony, Artificial Neural Network Application in Modelling Revenue Returns from Mobile Payment Services in Kenya, American Journal of Theoretical and Applied Statistics. Vol. 3, No. 3, 2014, pp. 60-64. doi: 10.11648/j.ajtas.20140303.11
References
[1]
Zhang, G., Patuwo, B. E. and Hu, M. Y. (1997) El-Shazly, M. R. and El-Shazly, H. E. (1997), ‘Com-paring the Forecasting Performance of Neural Networks and Forward Exchange Rates’, Journal of Multinational Financial Management, 7, 345-356.
[2]
Mwita, P., Franke, J., Odhiambo, R. and Waititu, A. (2005). On conditional quantiles: Direct Kernel Estimator and its Consistency. African Journal of Science and Technology, Vol. 6(2), 67-76.
[3]
Tang , Almeida and Fishwick, Simula-tion, Time series forecasting using neural networks vs. Box-Jenkins methodology ,November 1991, pp303- 310.
[4]
Medeiros M, Terasvirta, T, Rech, G. (2006) “Building Neural Network Models for Time Series: A Statistical Approach.” Journal of Forecasting. 25(1) pp. 49-75.
[5]
Zhang, G., Patuwo, B.E., Hu, M.Y. (1998), Forecasting with artificial neural networks: The state of the art International journal of forecasting, 14:35 -62.
[6]
Mahdavi Gh, Behmanesh MR (2005). The Forecasting of Stock Price of Investment Firms by Using Artificial Neural Networks. J. Econom. Res. 19(4): 211-233.
[7]
Zhong Luo, Liu Li-sheng. The application of Neural Network in Lifetime Prediction of Concrete. Journal of Wuhan University of Technology. 2002,17:79-81.
[8]
Teräsvirta T, Lin, C-FJ. 1993. Determining the number of hidden units in a single hidden-layer neural network model. Research Report 1993/7, Bank of Norway.
[9]
J. Yao, Y. Li and C. L. Tan, “Option price forecasting using neural networks,” OMEGA: Int. Journal of Management Science, vol. 28, pp 455-466, 2000.
[10]
HILL, T., OCONNOR, M. & REMUS, W. (1996) neural network models for time series forecasts. Management Science, 42, 1082-1092.
[11]
Pacelli1, V., Bevilaqua, V., Azzollini, M. (2011), An Artificial Neural Network Model to Forecast Exchanges rates, Journal for Intelligent Learning Systems and Applications, 3:57 - 69.
[12]
Kuan, C.M., Liu, T. (1995), forecasting exchange rates using feedforward and recurrent neural networks, Journal of Applied Econometrics, 10, (4): 347 – 364.
ADDRESS
Science Publishing Group
1 Rockefeller Plaza,
10th and 11th Floors,
New York, NY 10020
U.S.A.
Tel: (001)347-983-5186