Abstract  The problem we tackle concerns forecasting time ser ies in financial markets. AutoRegressive Moving&Average (ARMA) methods and computational intelligence have also been used to tackle this problem. We propose a novel method for time series forecasting based on a hybrid combinati on of ARMA and Gene Expression Programming (GEP) in duced models. Time series from financial domains often encapsulat e different linear and non&linear patterns. ARMA mo dels, although flexible, assume a linear form for the models. GEP evolves models adapting to the data without any res trictions with respect to the form of the model or its coefficients. Our appr oach benefits from the capability of ARMA to identi fy linear trends as well as GEP’s ability to obtain models that capture nonl inear patterns from data. Investigations are performed on real data sets. They show a definite improvement in the accuracy of forecasts of the hybrid method over pure ARMA and GEP used separately. Experimental results are analyzed and d iscussed. Conclusions and some directions for further research end the paper .    

References

[1] Aladag C., Egrioglub E., and Kadilar C., Forecasting Nonlinear Time Series with A Hybrid Methodology, Applied Mathematics Letters , vol. 22, no. 9, pp. 1467-1470, 2009.

[2] Armstrong J., Principles of Forecasting : A Handbook for Researchers and Practitioners , Kluwer Academic Publishers, 2001.

[3] Bautu E. and Barbulescu A., Mathematical Models of Climate Evolution in Dobrudja, Theoretical and Applied Climatology , vol. 100, no. 1-2, pp. 29-44, 2010.

[4] Belov I., Kabasinskas A., and Sakalauskas L., A Study of Stable Models of Stock Markets, Information Technology and Control , vol. 35, no. 1, pp. 34-56, 2006.

[5] Brockwell P. and Davies R., Introduction to Time Series , Springer, 2002.

[6] Clemen R., Combining Forecasts: A Review and Annotated Biography, International Journal of Forecasting , vol. 5, no. 4, pp. 559-583, 1989.

[7] Ferreira C., Gene Expression Programming: A New Adaptive Algorithm for Solving Problems, Journal of Complex Systems , vol. 13, no. 2, pp. 87-129, 2001.

[8] Ferreira C., Gene Expression Programming: Mathematical Modeling By An Artificial Intelligence , Springer-Verlag, 2006.

[9] De-Gooijer J. and Hyndman R., 25 Years of Time Series Forecasting, International Journal of Forecasting , vol. 22, no. 3, pp. 443-473, 2006.

[10] Guezouri M. and Mesbahi L., A New Approach Using Temporal Radial Basis Function in Chronological Series, The International Arab Journal of Information Technology , vol. 6, no. 1, pp. 85-90, 2009.

[11] Guidolin M., Hyde S., McMillan D., and Ono S., Non-Linear Predictability in Stock and Bond Returns: When and Where is it Exploitable?, International Journal of Forecasting, vol. 25, no. 2, pp. 373-399, 2009.

[12] Liang Y., Combining Seasonal Time Series ARIMA Method and Neural Networks with Genetic Algorithms for Predicting the Production Value of the Mechanical Industry in Taiwan, Neural Computing and Applications , vol. 18, no. 7, pp. 833-841, 2008.

[13] Lo A., The Adaptive Markets Hypothesis: Market Efficiency from An Evolutionary Perspective, Journal of Portfolio Management , vol. 30, no. 1, pp. 15-29, 2004.

[14] Lopes H. and Weinert W., EGIPSYS: An Enhanced Gene Expression Programming Approach for Symbolic Regression Problems, International Journal of Applied Mathematics and Computer Science , vol. 14, no. 3, pp. 375- 384, 2004.

[15] Pai P. and Lin C., A Hybrid ARIMA and Support Vector Machines Model in Stock Price Forecasting, Omega&The International Journal of Management Science , vol. 33, no. 6, pp. 497- 505, 2005.

[16] Plikynas D., Explaining International Investment Patterns: A Neural Network Approach, Information Technology and Control , vol. 34, no. 1, pp. 42-50, 2005.

[17] Reilly F. and Brown K., Investment Analysis and Portfolio Management , 5 th Edition Dryden Press, 1997.

[18] Schmidt M. and Lipson H., Distilling Free-Form Natural Laws from Experimental Data, Science Magazine, vol. 324, no. 5923, pp. 81-85, 2009.

[19] Santini M. and Tettamanzi A., Genetic Programming for Financial Time Series Prediction, in Proceedings of the 4 th European Conference on Genetic Programming , London, pp. 361-370, 2001.

[20] Sinclair T., Stekler H., and Kitzinger L., Directional Forecasts of GDP and In ation: A Joint Evaluation with An Application to Federal Reserve Predictions, Applied Economics Journal , vol. 42, no. 18, pp. 2289-2297, 2010.

[21] Wagner N., Michalewicz Z., Khouja M., and Mcgregor R., Time Series Forecasting for Dynamic Environments: The Dyfor Genetic Program Model, IEEE Transactions on Evolutionary Computation , vol. 11, no. 4, pp. 433-452, 2007.

[22] Zhang G., Time Series Forecasting Using A Hybrid ARMA and Neural Network Model, Journal of Neurocomputing, vol. 50, pp.159-175, 2003.

[23] Zhang G., Patuwo E., and Hu M., Forecasting with Artificial Neural Networks: The State of The Art, International Journal of Forecasting , vol. 14, no. 1, pp. 35-62, 1998.

[24] Zitar R., Genetic-Neural Approach Versus Classical Approach for Arabic Character Recognition Using Freeman Chain Features Extraction, The International Arab Journal of Information Technology , vol. 2, no. 4, pp. 291- 300, 2005. Alina Barbulescu received her BSc in Mathematics from Craiova University, her MSc in analysis and operators theory, from University of, Bucharest, Romania, PhD. in Mathematics from Al. I. Cuza University, Romania, and PhD. in Economics at Academy of Economic Studies, Bucharest, Romania. She published 90 articles

[18 ISI], and 18 books. She is a reviewer and editor at many journals. She was the cahirlady at many conferences. A Hybrid Approach for Modeling Financial Time Series 335 Elena Bautu received her BSc degree in computer science from Al. I. Cuza University, Romania in 2003, her MSc degree in applied mathematics from the Ovidius University, Constanta, Romania in 2005, and the PhD degree in computer science artificial intelligence from Al. I . Cuza University, Romania in 2010. Her research interests include evolutionary computation and data mining, especially data modeling, optimization, tim e series forecasting and inverse problems. She is aut hor of over 30 research articles, of which 15 are index ed in the ISI Thomson database. She is reviewer for geophysical research letters and IT Nuovo Cimento basic topics in physics.