Zastosowanie sieci neuronowych do prognozowania efektów cząstkowych zmiann w obrotach przedsiębiorstwa w układzie przestrzenno-branżowym. Część I

• Autorzy: Bieleninik E. , Mikuś J.

Warianty tytułu

EN

Application of neural networks to prediction of partial variation effects in company's turnover in a spatial-brand structure. Part I

• Języki publikacji: PL

Abstrakty

PL

Dokonano przeglądu zastosowań sieci neuronowych w prognozowaniu, ze szczególnym uwzględnieniem zastosowań ekonomicznych.. Przedstawiono ogólne zasady prognozy szeregów czasowych za pomocą sieci neuronowych. Zaprezentowano metodę Sterna-Styczyńskiego obliczania efektów cząstkowych zmian obrotów przedsiębiorstwa w układzie przestrzenno-branżowym.

EN

The paper examined the possibility to applying neural networks to prediction of partial variation effects in company's turnover in a spatial-brand structure. First, an extensive review if neural network applications for economic forecasting is provided. The general aspects of time series prediction using neural networks are discussed. The different architectures of neural networks are presented. Attention is mainly paid to the feed forward networks, recurrent networks and radial basis function networks. Some aspects of initial data processing are also discussed. Finally, the Stern-Tyszyński, method of calculating partial variation effects in company turnover in a spatial-brand structure is briefly presented. A practical example will be presented in the second part of the paper which will appear soon in this journal.

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Badania Operacyjne i Decyzje
• Rocznik: 2002
• Tom: nr 3-4
• Strony: 5--34
• Opis fizyczny: Bibliogr. 46 poz., rys.

Twórcy

autor

Bieleninik E.

• Zakład Informatyki Wydziału Informatyki i Zarządzania, Politechnika Wrocławska, Wybrzeże Wyspiańskiego 27, 50-370 Wrocław

autor

Mikuś J.

• Zakład Informatyki Wydziału Informatyki i Zarządzania, Politechnika Wrocławska, Wybrzeże Wyspiańskiego 27, 50-370 Wrocław

Bibliografia

• [1] ALMEIDA L.B., Backpropagation in Perceptrons with Feedback, In Neural Computers (Neuss 1987), Springer-Verlag. Berlin 1988, pp. 199-208.
• [2] ANKENBRAND T., TOMASSINI M., Multivariate Time Series Modelling of Financial Markets with Artificial Neural Networks, Pearson D.W., Steele N.C., Albrecht R.F., Artificial Neural Nets and Genetic Algorithms.
• [3] ASSIMAKOPOULUS V., A successive filtering technique for identifying long-term trends. Journal of Forecasting, 1995, 14, pp. 34-43. 
• [4] ATIYA A.F., SHAHEEN S.I., A Comparison Between Neural-Network Forecasting Techniques - Case Study liiver Flow Forecasting, IEEE Transactions on Neural Networks, Vol. 10, No. 2, March 1999.
• [5] BACK B., OOSTEROM G., SERE K., VAN WEZEL M., A Comparative Study of Neural Networks in Bankruptcy Prediction, Multiple paradigms for artificial intelligence: proceedings of contributed papers. Conference on AI Research in Finland, Turku Technology Center. 29-31 August, 1994.
• [6] BAZARNIK J„ GRABIŃSKI T., MYNARSKI S., SAGAN A., Badania marketingowe, Canadian Consortium of Management Schools, Akademia Ekonomiczna w Krakowie, Warszawa-Kraków 1992.
• [7] BEYER H.G.. DEGNER T., HAUSMANN J., RUJAN P., Short Term Prediction of Wind Speed and Power Output of a Wind Turbine with Neural Networks, Universität Oldenburg, 1998.
• [8] Box G.E.P., JENKINS G.M., Analiza szeregów czasowych. Prognozowanie i sterowanie, PWN, Warszawa 1983.
• [9] BROCKWELL P.J., DAVIS R.A., Introduction to Time Series and Forecasting, Springer-Verlag, New York, Inc. 1996.
• [10] CAMPOLUCCI P., UNCINI A., PIAZZA F., BHASKER D.R., On-line Learning Algorithms for Locally Recurrent Neural Networks, IEEE Trans, on Neural Networks, Vol. 10, No. 2, March 1999.
• [11] CHENOWETH T., OBRADOVIC Z., A Multi-Component Nonlinear Prediction System for the S&P 500 Index, Neurocomputing, 1996, Vol. 10(3), pp. 275-290.
• [12] DANIELS H., KAMP B., Application of MLP Networks to Bond Rating and House Pricing, Neural Comput & Applic, 1999, No. 8.
• [13] FERNANDEZ E., OLMEDA I., Bankruptcy Prediction with Artificial Neural Networks, From Natural to Artificial Neural Computation, Malaga-Torremolinos, June 1995.
• [14] FUNAHASKI K.I., On the approximate realization of continuous mappings by neural networks. Neural Networks, 1989, 2(3).
• |15] GATELY E„ Sieci neuronowe. Prognozowanie finansowe i projektowanie systemów transakcyjnych, Biblioteka Inwestora, Warszawa 1999.
• [16] GiROSSl F., POGGIO T., Networks and the best approximation property, Biological Cybernetics, 1990,63, pp. 169-176.
• [17] HECHT-NIELSEN R., Theory of the back-propagation neural network. In Proceedings of the Interna¬ional Joint Conference on Neural Networks. San Diego, CA, 1989, Vol. 1, pp. 593-605.
• [18] HERTZ J., KROGH A., PALMER R.G., Wstąp do teorii obliczeń neuronowych. WNT, Warszawa 1993.
• [19] KENDALL M., STUART A., The Advanced Theory of Statistics, vol. Ill, Hafner Publishing Co., New York 1976.
• [20] KHOTANZAD A., ABAYE A., ANNSTLF - A Neural-Network-Based Electric Load Forecasting System, IEEE Transactions on Neural Networks, Vol. 8, No.4, July 1997.
• [21] KORBICZ J., OBUCHOWICZ A., UCIŃSKI D.. Sztuczne sieci neuronowe - podstawy i zastosowania, Akademicka Oficyna Wydawnicza PU, Warszawa 1994.
• [22] KORCZAK J., JAJUGA K„ NOVAK J-P., DIZDAREVIC E., ROTER P., Genetic Evolution of Neural Network Model for Financial Market Forecasting, Université Louis Pasteur, Strassbourg 1996.
• [23] MASTERS T., Sieci neuronowe w praktyce, WNT, Warszawa 1986.
• [24] MEDLER D.A., A Brief History of Connect ionism, Neural Computing Surveys, 1998, No. 1.
• [25] MIKUŚ J., Prognozowanie efektów cząstkowych zmian w obrotach przedsiębiorstwa w układzie przestrzenno-branżowym, Badania Operacyjne i Decyzje, 1997, nr 2.
• [26] MIKUŚ J., AHMED ABO AMER, Badanie udziału i konkurencyjności przedsiębiorstwa na rynku w okresie retrospektywnym na przykładzie określonej firmy, cz. I, Badania Operacyjne i Decyzje, 2000, nr 3-4.
• [27] MlKUŚ J„ AHMED ABO AMER, Badanie udziału i konkurencyjności przedsiębiorstwa na rynku w okresie retrospektywnym na przykładzie określonej firmy, cz. II, Badania Operacyjne i Decyzje, 2000, nr 3-4.
• [28] MlZUNO H., KOSAKA M., YAJIMA H., Stock Market Prediction System based on Technical Analysis of Stock Index using Neural Network, The 15th 1MACS World Congress on Scientific Computation, Modelling and Applied Mathematics, Berlin, August 24-29, 1997.
• [29] MOLLER M.F., A scaled conjugated gradient algorithm for fast supervised training, Neural Networks, 1993, 6(40), pp. 525-533.
• [30] MONTE E., CALVET J.M., VILARRUBLA S.. Analysis of Industrial Economics by Means of Neural Nets, From Natural to Artificial Neural Computation. Malaga -Torremolinos, June 1995.
• [31] MOODY J., Economic Forecasting: Challenges and Neural Network Solutions, International Symposium on Artificial Neural Networks, Taiwan 1995.
• [32] OSSOWSKI S., Sieci neuronowe do przetwarzania informacji, Wyd. Politechniki Warszawskiej, Warszawa 2000.
• [33] RUMELHART D.E., HINTON G.E., WILLIAMS R.J., Learning representations by backpropagating errors. Nature, 1986, 323, pp. 533-536.
• [34] RUTKOWSKA D., PILIŃSKI M., RUTKOWSKI L., Sieci neuronowe, algorytmy genetyczne i systemy rozmyte. Wydawnictwo Naukowe PWN. Warszawa-Łódź 1997.
• [35] SARLE S.W., Stopped Training and Other Remedies for Overfitting, Proceedings of the 27th Symposium on the Interface, 1995.
• [36] SKURIKHIN A.H., SURKAN A.J., Neural Network Training Compared for Backprop, Quickprop and C.ascor in Energy Control Problems, Artificial Neural Nets and Genetic Algorithms.
• [37] TAKENS F., Detecting Strange Attractors in Turbulence, Lecture Notes in Mathematics, D. Rand and L. Young (eds.), Springer, Berlin 1981, pp. 366-381.
• [38] Tang Z., FISHWICH P.A., Feed-forward Neural Nets as Models for Time Series Forecasting, TR91- 008 Computer and Information Sciences, University of Florida, 1997.
• [39] TAYLOR S., Modelling Financial Time Series, Viley, Chichester 1992.
• [40] TYREF. E.W., LONG J. A., Forecasting Currency Exchange Rates: Neural Networks and the Random Walk Model, Third Inemational Conference on AI Applicationson Wall Street New York 1995.
• [41] VERMA B., Fast Training of Multilayer Perceptrons, IEEE Trans, on Neural Networks, Vol. 8, No. 6, November 1997.
• [42] WAN E., Time Series Prediction by Using a Connectionist Neural Network with Internal Delay Lines. In Time Series Prediction, Forecasting the Future and Understanding the Past, Eds by A. Weigend and N. Gershenfeld, SFI Studies in the Sciences of Complexity, Proc. Vd XVII, Addison-Wesley, 1994.
• [43] WANG S., An Adaptive Approach to Market Development Forecasting, Neural Computing & Applications (1999)8.
• [44] WEIGEND A.S., GERSHENFELD N.A., Time Series Prediction: Forecasting the Future and Understanding the Past, Proceedings of the NATO Advanced Research Workshop on Comparative Time Series Analysis, Santa Fe 1993.
• [45] WEIGEND A.S., HUBERMAN B.A., RUMELHART D.E., Prediction the future: A Connectionist Approach, International Journal of Neural Systems, 1990, Vol. 1.
• [46] WERBOS P.J., Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences, doctoral dissertation, Harvard University, 1974.