A neural network model for clearance sales outshopping behaviour

Abstract

This research applied a neural network model to study the clearance sales outshopping behaviour. The Guass Newton algorithm is selected to learn the pattern of the surveyed information. The architecture of this neural network is the multi-layer neural network. There are five hidden layers between the input layer and the output layer. We have used a neural network model to measure the impact among the retail area attributes, retail area satisfaction and retail area loyalty. This paper describes the impact of 27 input layers on five hidden layers. Then the impact of hidden layers on retail area loyalty and retail area satisfaction of the clearance sales outshoppers is obtained. The model fitness indices revealed that the proposed full neural network model to measure the clearance sales outshopping behaviour is significant. The development of model by retail area attributes, and their interpretation, was facilitated by collection of data across three trading areas. This neural network modelling approach to understanding clearance sales outshopping behaviour provides retail managers with information to support retail strategy development.