Sales forecasting for thin film transistor liquid crystal display products with data clustering and an evolving neural network model

Abstract

There are specific characteristics in the thin film transistor liquid crystal display (TFT-LCD) industry, such as unexpected demand fluctuation, customized products that each customer will designate a specific key component, long lead time of procurement, and short product life cycle. This research presents a genetic algorithm integrated with a neural network model for monthly sales forecasting of TFT-LCD products in Taiwan. The practical situation and its requirements are explained and two systematic approaches are discussed: (a) a K-means clustering for historic sales data and new sales is forecasted by mapping its inputs into one of these clustered data, and (b) a neural network integrated with a genetic algorithm for supervised learning of the functional behaviour of time-series data and their approximation. The evolving neural network model is applied for modelling the system's behaviour with the possibility of exploiting expert information and systematic optimization. The model has been tested and satisfying results are shown with practical data.

Keywords

sales forecasting genetic algorithm multiple regression analysis neural network Winter's exponential smoothing

References

Chang

P. C.

Wang

Y. W.

Liu

C. H.

Genetic algorithm back-propagation network for PCB sales forecasting. Lecture Notes in Computer Sei20053610364–373.

Chang

P. C.

Wang

Y. W.

Genetic algorithm delphi and back-propagation model for sales forecasting in PCB industry. Expert Systems with Applic.200630 (4)715–726.

Chang

P. C.

Wang

Y. W.

Tsai

C. Y.

Evolving neural network for printed circuit board sales. Expert Systems with Applic.200529 (1)83–92.

Serajzadeh

Prediction of temperature and velocity distributions during hot rolling using finite elements and neural network. Proc. IMechE, Part B: J. Engineering Manufacture2006220 (B7)1069–1075.

Zhang

Y. M.

Kovacevic

Neurofuzzy algorithm model-based predictive control of weld fusion zone geometry. IEEE Trans Fuzzy Systems19986 (3)389–401.

Johnson

R. A.

Wichern

D. W.

Applied multivari-ate statistical analysis2002 (Prentice-HallNew Jersey).

Bakirtzls

G. V.

A neural network short term load forecasting model for the Greek power system. IEEE Trans. Pwer Systems199611 (2)858–863.

Rao

C. H.

Srinivasa

Online prediction of diffusion wear on the flank through tool tip temperature in turning using artificial neural networks. Proc. IMechE, Part B: J. Engineering Manufacture2006220 (B12)2069–2076.

Krolzig

H. M.

Toro

Multi period forecasting in Stock Markets: A paradox solved. Decision Support Systems200437531–542.

10.

Leigh

Purvis

Ragusa

J. M.

Forecasting the NYSE composite Index with technical analysis, pattern recognizer, neural network, and genetic algorithm: A case study in romantic decision support. Decision Support Systems200232361–377.

11.

Burgess

A. P. N.

Bentz

Neural networks in financial engineering: A study in methodology. IEEE Trans. Neural Networks19978 (6)1222–1267.

12.

Bollerslev

Generalized autoregressive conditional heteroskedaticicty. J. Econometrics198652307–327.

13.

Campbell

J. Y.

A. W.

MacKinlay

A. C.

The econometrics of financial markets1997 (Princeton University Press.

14.

Bezdek

J. C.

Pattern recognition with genetic algorithm objective function algorithms1981 (PlenumNew York).

15.

Dare

R. N.

Use of the adaptive genetic algorithm clustering algorithm to detect lines in digital images. Proc. SPIE Conf. Intelligent Robots and Computer Vision19891192 (2)600–611.

16.

Lee

S. H.

Et al. A neural network approach to the modelling and analysis of stereolithography processes. Proc. Instn Mech. Engrs, Part B: J. Engineering Manufacture2001215 (B12)1719–1733.

17.

Piras

Buchenel Jaccard

Heterogeneous artificial neural network for short term electrical load forecasting. IEEE Trans. Pwer Systems199611 (1)397–402.

18.

Chang

P. T.

Huang

L. C.

Lin

H. J.

The fuzzy Delphi method via fuzzy statistics and membership function fitting and an application to the human resources. Fuzzy Sets and Systems2000112511–520.

19.

Hsu

C. C.

Chen

C. Y.

Applications of improved grey prediction model for power demand forecasting. Energy Conversion Mgmt2003442241–2249.

20.

Lin

C. T.

Lee

C.-S. G.

Neural-network-based genetic algorithm inference systems. IEEE Trans, on Computer199140 (12)1320–1336.

21.

Goldberg

D. A.

Genetic algorithms in search, optimization, and machine learning. Reading1989, (Addison-WesleyMA).