A neural network model for sales forecasting

Abstract

The value of neural networks in solving complex nondeterministic problems has been demonstrated across a broad range of applications. A promising area for neural network application is that of economic forecasting. This study investigates the application of the connectionist paradigm to sales forecasting. A neural network model for the prediction of sales levels was developed and the sales forecasts produced by the network were compared with the actual sales figures, as well as with the forecasts made by the marketing managers. These studies indicate that neural networks can be successfully applied to this problem.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>