Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

PL EN


2009 | 10 | 1 | 252-264

Article title

BADANIA EFEKTYWNOŚCI PREDYKCYJNEJ MODELU KLASY GMDH OPARTEGO NA ZACHOWANIU UCZESTNIKÓW RYNKU WALUTOWEGO

Content

Title variants

EN
PREDICTION EFFICIENCY INVESTIGATION OF GMDH-CLASS MODEL BASED ON BEHAVIOURING OF CURRENCY MARKET USERS

Languages of publication

PL EN

Abstracts

PL
W pracy przedstawiono wyniki eksperymentu przeprowadzonego w celu predykcyjnym na rynku walutowym. Założono, że rynek nie jest efektywny i daje się z przeszłości wyekstrahować wiedzę o błędach popełnionych przez uczestników wybranej platformy brokerskiej. Dla wykonania predykcji wykorzystano zmodyfikowaną metodę GMDH (Group Method of Data Handling) umożliwiającą sukcesywny wybór nieliniowego modelu wielomianowego najlepiej w danym kroku opisującego rynek. Przedstawiono interesujące wyniki eksperymentu na danych historycznych potwierdzającego użyteczność metody. Danymi wejściowymi były zarejestrowane na platformie zachowania inwestorów – rozkład otwartych pozycji i złożonych zleceń. Stąd – rozpatrywane podejście można zaliczyć do modelowania behawioralnego.
EN
The paper presents the results of an experiment concerning prediction of the foreign exchange market. It was assumed, that the market is not efficient and that it is possible to extract from the past the knowledge regarding traders’ mistakes. A modified version of GMDH method was used for prediction, which allows for successive selection of such nonlinear polynomial model, that describes the market most adequately at a particular moment. Presented results confirm usefulness of the proposed method. Input data was comprised of the information on traders behaviour, registered by the brokerage platform, regarding open positions and orders. Hence, such a solution can be thought of as behavioural modelling.

Contributors

  • Wydział Informatyki, ZUT

References

  • Barberis N., Shleifer A. Vishny R. A model of investor sentiment. Journal of Fi-nancial Economics 49 (1998), str.307-343.
  • DeBondt W., Thaler R. Does the stock market overreact? Finance of Journal 40(3) 1985,str.793-805.
  • Dehuri S., Cho S.-B. Multicriterion Pareto based particle swarm optimized poly-nomial neural network for classification: A review and state-of-the-art. Computer Science Review 3(2009) str.19-40.
  • Fama E.F. Market efficiency, long-term returns, and behavioral finance. Journal of Finacial Economics 49 (1998) str.283-306.
  • Hia Jong Teoh, Tai Liang Chen, Ching Hsue Cheng, Hsing Hui Chu. A hybrid multi-order fuzzy time series for forcasting stock markets. Expert Systems with Applications 36 (2009)str. 7888-7897.
  • Ivakhnenko A., Ivakhnenko G., Mueller J. Self- organization of Neural Network with Active Neurons. Pattern Recognition and Image Analysis 1999 v.4/2 str.185-196.
  • Ivakhnenko A., Ivakhnenko G., Problems of Further Development of the Group Method of Data Handling Algorithms. Part I. Pattern Recognition and Image Analysis vol.10 No.2, 2000, str.. 187-194.
  • Lemke F., Mueller J. A. Self- Self- Organizing Data Mining A Portfolio Trading System. Journal of Commputational Intelligence in Finance, 1997/05 str. 12-26
  • Madala H.R, Ivakhnenko A., Inductive Learning Algorithms for Complex Systems Modeling. CRC Press, 1994.
  • Park B.J., Oh S.K., Ahn T.C., Pedrycz W. A study on multilayer fuzzy polynomial interference system based on an extended GMDH algorithm. Proc. 8th IEEE Inf. Conference on Fuzzy Systems, Seoul 1999.
  • Piper J. The Way to Trade, Harriman Modern Classic, 2006.
  • Sheng-Hsun Hsu, Po-An Hsieh, Ting-Chih Chih, Kuei-Chu Hsu. A two-stage ar-chitecture for stock price forecasting by integrating self-organizing map and sup-port vector regression. Expert Systems with Applications 36(2009) 7947-7951
  • Shleifer A. An inefficient market: An introduction to behavioral finance. Clarendon Lectures. Oxford University Press 2000.
  • Sung-Kwun Oh, Pedrycz W. The design of self-organizing Polynomial Neural Networks. Information Sciences, 141 (2002) str. 237-258
  • Wilinski A. GMDH Based Computational Intelligence Method for Prediction of Financial Markets. “Intellectual Systems of Decision Making and The Problems of Computational Intelligence (ISDMCI’2008) , Eupatoria, Tom 1 cz.1, 2008.
  • Wiliński A., Czapiewski P. GMDH-based Multiple Prediction of Financial Mar-kets. Polish Journal of Environmental Studies vol.18 No 4a, 2008.
  • Zhang Yudong, Wu Lenan. Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network. Expert Systems with Applica-tions 36(2009) str. 8849-8854.
  • Oanda, www.oanda.com dostęp kwiecień – listopad 2008.
  • Wanadoo, www.wanadoo.com dostęp lipiec 2008.

Document Type

Publication order reference

Identifiers

YADDA identifier

bwmeta1.element.desklight-57cc9541-5b9b-46b9-8384-d205a046bd69
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.