Forecasting Exchange Rates with Mixed Models

Authors

  • Laura Maria Badea The Bucharest University of Economic Studies

Keywords:

machine learning techniques, Artificial Neural Networks, ARIMA, exchange rate forecasting, learning algorithms, BFGS optimization

Abstract

Gaining accuracy in exchange rate forecasting applications provides true benefits for financial activities. Supported today by the advancements in computing power, machine learning techniques provide good alternatives to traditional time series estimation methods. Very approached in time series forecasting are Artificial Neural Networks (ANNs) which offer robust results and allow a flexible data manipulation. When integrating both, the “white-box” feature of conventional methods and the complexity of machine learning techniques, forecasting models perform even better in terms of generated errors. In this study, input variables (independent variables) are selected using an ARIMA technique and are further employed in differently configured multilayered feed-forward neural networks using Broyden-Fletcher-Goldfarb-Shanno (BFGS) optimization algorithm to perform predictions on EUR/RON and CHF/RON exchange rates. Results in terms of mean squared error highlight good results when using mixed models.

Author Biography

Laura Maria Badea, The Bucharest University of Economic Studies

PhD stdent, Dep. of Cybernetics

References

G.E.P. Box and G.M. Jenkins, Time Series Analysis: Forecasting and Control, San Francisco: Holden-Day, 1970

J. T. Yao, H.-L. Poh, and T. Jasic, Foreign Exchange Rates Forecasting with Neural Networks, International Conference on Neural Information Processing (ICONIP'96), Hong Kong, Sept. 24-27, 1996, pp. 754-759

T. Hill, M. O’Connor and W. Remus, Neural Network Models for Time Series Forecasts, Management Science, Vol. 42, 1996, pp. 1082-1092

G. Zhang and M.Y. Hu, Neural Network Forecasting of the British Pound/US Dollar Exchange Rate, International Journal of Management Science, Vol. 26, 1998, No. 4, pp. 495-506

C.L. Dunis and M. Williams, Modelling and Trading the EUR/USD Exchange Rate: Do Neural Network Models Perform Better?, Derivatives Use, Trading and Regulation, Vol. 8, No. 3, 2002, pp. 211–239

J. Kamruzzaman and R.A. Sarker, Comparing ANN Based Models with ARIMA for Prediction of Forex Rates, ASOR Bulletin, Vol. 22, 2003, pp. 2-11

C. Panda and V. Narasimhan, Forecasting Exchange Rate Better with Artificial Neural Network, Journal of Policy Modeling, Vol. 29, 2007, pp. 227–236

C.L. Dunis, J. Laws and G. Sermpinis, The Robustness of Neural Networks for Modelling and Trading the EUR/USD Exchange Rate at the ECB Fixing, Journal of Derivatives & Hedge Funds, Vol. 15, 2009, pp. 186-205

A.N. Kia, M. Fathian and M.R. Gholamian, Using MLP and RBF Neural Networks to Improve the Prediction of Exchange Rate Time Series with ARIMA, International Journal of Information and Electronics Engineering, Vol. 2, No. 4, 2012, pp. 543-546

L. Yu, S. Wang, W. Huang and K.K. Lai, Are Foreign Exchange Rates Predictable? A Survey from Artificial Neural Networks Perspective, Scientific Inquiry: A Journal of International Institute for General Systems Studies, Vol. 8, No. 2, 2007, pp. 207-228

G.S. Atsalakis and K.P. Valavanis, Surveying Stock Market Forecasting Techniques – Part II: Soft Computing Methods, Expert Systems with Applications, Vol. 36, 2008, pp. 5932-5941

R.C. Schweitzer and J.B. Morris, A Tutorial on Neural Networks Using the Broyden-Fletcher-Goldfarb-Shanno (BFGS) Training Algorithm and Molecular Descriptors With Application to the Prediction of Dielectric Constants Through the Development of Quantitative Structure Property Relationships (QSPRs), Army Research Laboratory, 2000

C. Broyden, The Convergence of a Class of Double-Rank Minimization Algorithms, Journal of Inst. Mathematical Applications, Vol. 6, 1970, pp. 222-231

R. Fletcher, A New Approach to Variable Metric Algorithms, Computer Journal, Vol. 13, 1970, pp. 317-322

D. Goldfarb, A Family of Variable-Metric Methods Derived by Variational Means, Mathematical Computations, Vol. 24, 1970, pp. 23-26

D. Shanno, Conditioning of Quasi-Newton Methods for Function Minimization, Mathematical Computations, Vol. 24, 1970, pp. 647-656

B. Oancea and S.C. Ciucu, Time Series Forecasting Using Neural Networks, Proceedings of The 7th International Scientific Conference Challenges of the Knowledge Society, Bucharest, 2013, pp. 1401-1408

S. Knerr, L. Personnaz, G. Dreyfus, Handwritten Digit Recognition by Neural Networks with Single-Layer Training, IEEE Transactions on Neural Networks, Vol.3, No. 6, 1992, pp. 962-968

Downloads

Published

2013-06-30

How to Cite

Badea, L. M. (2013). Forecasting Exchange Rates with Mixed Models. Journal of Mobile, Embedded and Distributed Systems, 5(2), 84-89. Retrieved from http://jmeds.eu/index.php/jmeds/article/view/Forecasting_Exchange_Rates_with_Mixed_Models

Issue

Vol. 5 No. 2 (2013): Mobile technologies in Education and Economics

Section

Articles

License

Authors who publish with this journal agree to the following terms:


    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

    1. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

    1. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).

    1. The author(s) is responsible for the correctness and legality of the paper content.

    1. Papers that are copyrighted or published will not be taken into consideration for publication in JMEDS It is the author(s) responsibility to ensure that the paper does not cause any copyright infringements and other problems.

    1. It is the responsibility of the author(s) to obtain all necessary copyright release permissions for the use of any copyrighted materials in the paper prior to the submission.

  1. The Author(s) retains the right to reuse any portion of the paper, in future works, including books, lectures and presentations in all media, with the condition that the publication by JMEDS is properly credited and referenced.
Creative Commons License
JMEDS articles by Journal of Mobile, Embedded and Distributed Systems (JMEDS) is licensed under a Creative Commons Attribution 4.0 International License.
Based on a work at http://jmeds.eu.
Permissions beyond the scope of this license may be available at http://jmeds.eu/index.php/jmeds/about/submissions#copyrightNotice.