Title: Adaptive demand-forecasting approach based on principal components time-series: an application of data-mining technique to the detection of market movement

Authors: Toshio Sugihara

Addresses: Faculty of Economics, Nagasaki University, Katafuchi 4-2-1, Nagasaki, Japan

Abstract: In this study, an adaptive demand-forecasting approach adopting the data-mining technique that detects the correlation between the target variable and other related elements, is proposed. Also included is the time-series analysis scheme based on the state-space approach This approach has two characteristic points. One is the state-space that is formed by principal components composed of various market variables. Another is the self organisation of the state-space using a neural network. This latter approach is applied to two cases of demand-forecasting. Some comparisons of forecasting accuracy (extrapolation test) with this approach and non-self-organising models (AR, etc) are used to evaluate the effectiveness of the proposed approach. Consequently, we achieved significantly higher accuracy using this approach compared to other approaches.

Keywords: adaptive demand-forecasting; data-mining approach, (Extended) Kalman Filter; principal component analysis; neural networks.

DOI: 10.1504/IJMDM.2002.002470

International Journal of Management and Decision Making, 2002 Vol.3 No.2, pp.151-164

Published online: 18 Jul 2003 *

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