Abstract In this paper, we examine and discuss results of financial time series prediction by using a combination of wavelet transform, neural networks and statistical time series analytical techniques. The analyzed hybrid model combines the capabilities of wavelet packet transform and neural networks that can capture hidden but crucial structure attributes embedded in the time series. The input data is decomposed into a wavelet representation using two different resolution levels. For each of the new time series, a neural network is created, trained and used for prediction. In order to create an aggregate forecast, the individual predictions are combined with statistical features extracted from the original input. Additional to the conclusion that the increase in resolution level does not improve the prediction accuracy, the analysis of obtained results indicates that the suggested model presents satisfactory predictor. The results also serve as an indication that denoising process generates more accurate results when applied.

References

[1] Al-wazan H., Ibraheem K., and Salim A., A Hybrid Algorithm to Forecast Enrolment Based on Genetic Algorithms and Fuzzy Time Series, The International Arab Journal of Information Technology, vol. 11, no. 3, pp. 250-257, 2014.

[2] Bozic J. and Babic D., Predicting the EUR/RSD Exchange Rate Using Wavelets and Neural Network, in Proceedings of International Conference on Applied Internet and Information Technologies, Zrenjanin, pp. 108-112, 2013.

[3] Bozic J., Vukotic S., and Babic D., Prediction of the RSD Exchange Rate by Using Wavelets and Neural Networks, in Proceedings of the 19th Telecommunications Forum, Belgrade, pp. 703- 706, 2011.

[4] Box G., Jenkins G., and Reinsel G., Time Series Analysis: Forecasting and Control, John Wiley and Sons, 2008.

[5] Fan S., Ji T., Gordon W., and Rickard B., Forecasting Baltic Dirty Tanker Index by Applying Wavelet Neural Networks, Journal of Transportation Technologies, vol. 3, no. 1, pp. 68-87, 2013.

[6] Orozco J. and Garcia C., Detecting Pathologies From Infant Cry Applying Scaled Conjugate Gradient Neural Networks, in Proceedings of the European Symposium on Artificial Neural Networks, Bruges, pp. 349-354, 2003.

[7] Gencay R., Selcuk F., and Whitcher B., An Introduction to Wavelets and Other Filtering Methods in Finance and Economics, Academic Press, 2002.

[8] Gil P., Cortes J., Hernandez S., and Aquino V., A Neural Network Scheme for Long-Term Forecasting of Chaotic Time Series, Neural Processing Letters, vol. 33, no. 3, pp. 215-233, 2011.

[9] Hippert H., Pedreira C., and Souza R., Neural Networks for Short-Term Load Forecasting: A Review and Evaluation, IEEE Transactions on Power Systems, vol. 16, no. 1, pp. 44-54, 2001.

[10] Holschneider M., Wavelets: An Analysis Tool, Oxford University Press, 1999.

[11] Incze A., Ileana I., and Rotar C., The Optimization of Feed Forward Neural Networks Structure Using Genetic Algorithms, in Proceedings of the International Conference on Theory and Applications of Mathematics and Informatics, Thessaloniki, pp. 223-234, 2004.

[12] Kaastr I. and Boyd M., Designing a Neural Network for Forecasting Financial and Economic Time Series, Neurocomputing, vol. 10, no. 3, pp. 215-236, 1996.

[13] Kamruzzaman J., Begg R., and Sarker R., Artificial Neural Networks in Finance and Manufacturing, Idea Group Inc, 2006.

[14] Kamruzzaman J. and Sarker R., Comparing ANN Based Models with ARIMA for Prediction of Forex Rates, Asor Bulletin, vol. 22, no.2, pp. 2-11, 2003.

[15] Minu K., Lineesh M., and Jessy C., Wavelet Neural Networks for Nonlinear Time Series Analysis, Applied Mathematical Sciences, vol. 4, no. 50, pp. 2485-2595, 2010.

[16] Murtagh F., Starck J., and Renaud O., On Neuro-wavelet Modeling, Decision Support Systems, vol. 37, no. 4, pp. 475-484, 2004.

[17] Ortega L. and Khashanah K., A Neuro-wavelet Model for the Short-Term Forecasting of High- Frequency Time Series of Stock Returns, Journal of Forecasting, vol. 33, no. 2, pp. 134- 146, 2013.

[18] Pacelli V., Bevilacqua V., and Azzollini M., An Artificial Neural Network Model to Forecast Exchange Rates, Journal of Intelligent Learning Systems and Applications, vol. 3, no. 2, pp. 57- 69, 2008.

[19] Renaud O., Stark J., and Murtagh F., Prediction Based on a Multiscale Decomposition, International Journal of Wavelets, Multiresolution and Information Processing, vol. 1, no. 2, pp. 217-232, 2003.

[20] Vonesch C., Blu T., and Unser M., Generalized Daubechies Wavelet Families, IEEE Transactions on Signal Processing, vol. 55, no. 9, pp. 4415-4429, 2007. Financial Time Series Forecasting Using Hybrid Wavelet-Neural Model 57

[21] Yao J., Li Y., and Tan C., Option Price Forecasting using Neural Networks, Omega, vol. 28, no. 4, pp. 455-466, 2000.

[22] Yao J. and Tan, C., A Case Study on Using Neural Networks to Perform Technical Forecasting of Forex, Neurocomputing, vol. 34, no. 1-4, pp. 79-98, 2000.

[23] Yu L., Wang S., Huang W., and Lai K., Are Foreign Exchange Rates Predictable? Scientific Inquiry, A Journal of International Institute for General Systems Studies, vol. 8, no. 2, pp. 207- 228, 2007.

[24] Zhang G. and Qi M., Neural Network Forecasting for Seasonal and Trend Time Series, European Journal of Operational Research, vol. 160, no. 2, pp. 501-514, 2005. Jovana Bozic obtained her Diploma Engineer degree in electrical engineering in 2007 from the School of Electrical Engineering, University of Belgrade, Serbia. She is currently a PhD candidate at the School of Computing, Department of Signal processing in telecommunications, of the Union University. Her main research interests are in the areas of time series prediction, artificial neural networks and wavelet-based signal processing. She has published several papers in national and international conferences and journals. Djordje Babic obtained his Diploma Engineer degree in 1999 at the School of Electrical Engineering, University of Belgrade. He defended his doctoral thesis in the field of signal processing in telecommunications at Tampere University of Technology, Finland, in 2004. From 1999 to 2004, he was employed at the Institute of Telecommunications, Tampere University of Technology. Since 2008 he has been employed at the School of Computing, Belgrade, as an associate professor in the field of networked computer systems. He conducts research in the field of signal processing in telecommunications, multirate signal processing. He has published over 30 articles in different international journals and at international conferences.