This paper analyses the hybridization of intelligent techniques for time series data prediction of FX rate INR/USD to alleviate the limitation of statistical methods for non-linear data. This paper uses the feature extraction to extract the new features, five new features are extracted from the one original feature of INR/USD i.e Next week FX. Wavelet technique has been used for pre-processing the chaotic data series and prepares the de-noised data to get accurate prediction result. ANFIS is uses the non-linear functions and identify the non-linear components to predict the time series data with its fluctuating behaviour. Result came from ANFIS is compare with ANN technique, Error Back Propagation Network (EBPN). The empirical result of Hybridization of Wavelet and Feature selection with ANFIS and ANN shows that ANFIS produces the best prediction result with MAPE 1.568, MAE0.0136 and RMSE 0.0174.

ANFIS(Adaptive Neuro-Fuzzy Inference System), ANN (Artificial Neural Network), Wavelet, Feature extraction

[1] R. Handa, H. S. Hota, and S. R. Tandan, “Stock Market Prediction with Various Technical,” vol. 3, no. 1, pp. 604–608, 2015.
[2] J. Shing and R. Jang, “anfis 93.pdf,” IEEE Trans. Syst. MAN Cibern., vol. 23, no. 03, pp. 665–685, 1993.
[3] N. Walia, H. Singh, and A. Sharma, “ANFIS : Adaptive Neuro-Fuzzy Inference System- A Survey,” Int. J. Comput. Appl., vol. 123, no. 13, pp. 32–38, 2015.
[4] M. Gherman, R. Terebes, and M. Borda, “TIME SERIES ANALYSIS USING WAVELETS AND GJR-GARCH MODELS,” no. Eusipco, pp. 2138–2142, 2012.
[5] M. Sifuzzaman, M. R. Islam, and M. Z. Ali, “Application of Wavelet Transform and its Advantages Compared to Fourier Transform,” vol. 13, pp. 121–134, 2009.
[6] H. Mo, J. Wang, and H. Niu, “Exponent back propagation neural network forecasting for financial cross-correlation relationship,” Expert Syst. Appl., vol. 53, pp. 106–116, 2016.
[7] S. Acadmy, “IMAGE FUSION BASED ON STATIONARY WAVELET,” Int. J. Adv. Eng. Res. Stud., vol. 2, no. 4, pp. 99–101, 2013.
[8] C. Tan, “Financial Time Series Forecasting Using Improved Wavelet Neural Network Master ’ s Thesis,” 2009.
[9] B. Kozlowski, “Time series denoising with wavelet transform,” J. Telecommun. Inf. Technol., no. 1, pp. 91–95, 2005.
[10] S. Barak, J. Heidary, and T. Tichý, “Wrapper ANFIS-ICA method to do stock market timing and feature selection on the basis of Japanese Candlestick,” vol. 42, pp. 9221–9235, 2015.
[11] A. Kazem, E. Sharifi, F. K. Hussain, M. Saberi, and O. K. Hussain, “Support vector regression with chaos-based firefly algorithm for stock market price forecasting,” Appl. Soft Comput. J., vol. 13, no. 2, pp. 947–958, 2013.
[12] C. H. Su and C. H. Cheng, “A hybrid fuzzy time series model based on ANFIS and integrated nonlinear feature selection method for forecasting stock,” Neurocomputing, vol. 205, pp. 264–273, 2016.
[13] L. Wei, “A hybrid ANFIS model based on empirical mode decomposition for stock time series forecasting,” Appl. Soft Comput. J., vol. 42, pp. 368–376, 2016.
[14] R. Handa, A. K. Shrivas, and H. S. Hota, “PREDICTION OF FOREX DATA USING NEURAL NETWORK,” vol. 14, no. 2, pp. 111–116, 2017.
[15] L. Wang and S. Gupta, “Time Series Analysis, Modeling and Applications,” vol. 47, pp. 229–247, 2013.
[16] MathWorks, “Wavelet Denoising,” pp. 1–22, 2017.
[17] J. Z. Wang, J. J. Wang, Z. G. Zhang, and S. P. Guo, “Forecasting stock indices with back propagation neural network,” Expert Syst. Appl., vol. 38, no. 11, pp. 14346–14355, 2011.
[18] J. S. R. Jang and C. T. Sun, “Neuro-Fuzzy Modeling and Control,” Proc. IEEE, vol. 83, no. 3, pp. 378–406, 1995.
[19] K. Rezaei, R. Hosseini, and M. Mazinani, “a F Uzzy I Nference S Ystem F or a Ssessment of T He S Everity of T He,” pp. 263–271, 2014.