FEEDFORWARD NEURAL NETWORKS AND THE FORECASTING OF MULTI-SECTIONAL DEMAND FOR TELECOM SERVICES: A COMPARATIVE STUDY OF EFFECTIVENESS FOR HOURLY DATA

Keywords: Prediction System, feedforward neural network, regressive-neural model, forecasting.

Abstract

The presented research focuses on the construction of a model to effectively forecast demand for connection services – it is thus relevant to the Prediction System (PS) of telecom operators. The article contains results of comparative studies regarding the effectiveness of neural network models and regressive-neural (integrated) models, in terms of their short-term forecasting abilities for multi-sectional demand of telecom services. The feedforward neural network was used as the neural network model. A regressive-neural model was constructed by fusing the dichotomous linear regression of multi-sectional demand and the feedforward neural network that was used to model the residuals of the regression model (i.e. the residual variability). The response variable was the hourly counted seconds of outgoing calls within the framework of the selected operator network. The calls were analysed within: type of 24 hours (e.g. weekday/weekend), connection categories, and subscriber groups. For both compared models 35 explanatory variables were specified and used in the estimation process. The results show that the regressive-neural model is characterised by higher approximation and predictive capabilities than the non-integrated neural model.

Downloads

Download data is not yet available.

References

Box, G.E.P., Jenkins, G.M., Reinsel, G.C. (1994). Time Series Analysis. Forecasting and Control. Prentice Hall, Englewood Clifs.

Daft, R.L., Marcic, D. (2011). Understanding Management. South-Western Cengage Learning, Mason.

Dittmann, P., Szabela-Pasierbińska, E., Dittmann, I., Szpulak, A. (2011). Prognozowanie w za rządzaniu sprzedażą i finansami przedsiębiorstwa. Wolters Kluwer Polska, Warszawa.

Griffin, R. (2015). Fundamentals of Management. Cengage Learning, Boston.

Kaczmarczyk, P. (2006). Neuronowe i regresyjno-neuronowe modelowanie i prognozowanie zjawisk ekonomicznych.

Empiryczna weryfikacja porównawcza. Zeszyty Naukowe PWSZ w Płocku, Nauki Ekonomiczne, 5, 209–218.

Kaczmarczyk, P. (2016). Integrated Model of Demand for Telephone Services in Terms of Mi croeconometrics. Folia Oeconomica Stetinensia, 16, 72–83. https://doi.org/10.1515/foli-2016-0026

Kaczmarczyk, P. (2017). Microeconometric Analysis of Telecommunication Services Market with the Use of SARIMA Models. Dynamic Econometric Models, 17, 41–57. https://doi.org/10.12775/DEM.2017.003

Makridakis, S., Wheelwright, S.C. (1989). Forecasting Methods for Management. J. Wiley, New York.

Makridakis, S., Wheelwright, S.C., Hyndman, R.J. (1998). Forecasting Methods and Applica tions. J. Wiley, New

York.

Masters, T. (1993). Practical Neural Network Recipes in C++. Academic Press, Inc, San Diego.

Rojas, R. (2013). Neural Networks: A systematic introduction. Springer Science & Business Media, Berlin.

Smith, K.A., Gupta, J.N.D. (2002). Neural Networks in Business: Techniques an Applications. PA: Idea Group Publishing, Hershey.

Tiliouine, H. (2007). Comparative study of learning methods for artificial network. Pomiary Automatyka Kontrola, 4, 117‒121.

Zhang G.P. (2004). Neural Networks in Business Forecasting. PA: Idea Group Publishing, Hershey.

Published
2020-09-18
How to Cite
Kaczmarczyk, P. (2020). FEEDFORWARD NEURAL NETWORKS AND THE FORECASTING OF MULTI-SECTIONAL DEMAND FOR TELECOM SERVICES: A COMPARATIVE STUDY OF EFFECTIVENESS FOR HOURLY DATA. Acta Scientiarum Polonorum. Oeconomia, 19(3), 13-25. https://doi.org/10.22630/ASPE.2020.19.3.24