Title: Long-range prediction of retail sales using recurrent radial basis function neural network

Authors: Minakhi Rout; Babita Majhi

Addresses: Department of Computer Science and Engineering, Institute of Technical Education and Research (ITER), Siksha 'O' Anusandhan University, Bhubaneswar, India ' Department of Computer Science and Information Technology, Guru Ghasidas Vishwavidyalaya Central University, Bilaspur, India

Abstract: The literature survey on sales forecasting reveals that few works have been reported on long-range forecasting of sale volumes. On the other hand, there is a need of such long-range forecasting of sales data to devise suitable organisational strategy. The existing soft computing-based forecasting models provide poor prediction performance. Keeping this in view a new soft computing model is developed and utilised for prediction of seasonally adjusted (SA) and non-seasonally adjusted (NSA) sales volumes up to 24 months. The simulation results of real-life data show an excellent prediction performance compared to that of four other contemporary soft computing models.

Keywords: sales forecasting; retail sales; artificial neural networks; MLANN; multi-layer ANNs; FLANN; functional link ANNs; RNNs; recurrent neural networks; RBF; radial basis function; RRBFNN; long-range forecasting; simulation.

DOI: 10.1504/IJFIP.2015.070053

International Journal of Foresight and Innovation Policy, 2015 Vol.10 No.1, pp.29 - 47

Received: 17 Jun 2013
Accepted: 07 Mar 2014

Published online: 25 Jun 2015 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article