股價預測是一個成熟的研究領域，統計學或機器學習等方法在這個領域被廣泛應用。然而，金融數據中的自然噪音對人類和計算機都構成挑戰。傅立葉變換在頻域去噪方面效果顯著，但發散問題仍然存在挑戰。為了應對這種發散，先前的方法提出使用隨機遊走來構造填充數據，從而孤立發散。然而，隨機遊走生成的填充數據引入了噪音，阻礙了更一致填充數據的推導，並增加了預測誤差。在這項研究中，我們介紹了一種基於 stationary bootstrap 填充和快速傅立葉變換 (SB-FTD) 的去噪技術。這種方法消除了頻域中的噪音，並提供了一種更一致的數據填充方法。這種方法改進了隨機遊走填充方法，並允許在不受噪音影響的環境中去噪原始序列的頻域特徵。我們的實證結果表明，所提出的去噪方法在預測能力和解釋能力方面優於隨機遊走填充基礎的去噪，並在多個金融指數 (包括但不限於 S&P 500、DJI 和 TWII) 上得到了驗證。

Stock price prediction constitutes a well-established area of research, with methods such as statistics or machine learning widely used in this field. Nevertheless, the natural noise in financial sequences poses challenges for both humans and computers. Fourier transform is effective for denoising in the frequency domain, but the issue of divergence presents a challenge. To address this divergence, previous approaches proposed using a random walk to construct padding data, isolating the divergence. However, the padding data generated by the random walk introduces noise, preventing the derivation of more coherent padding data and leading to an increased prediction error. In this study, we introduce a denoising technique based on stationary bootstrap padding and fast Fourier transform (SB-FTD). This method eliminates noise in the frequency domain and provides a more coherent approach to data padding. This method improves the random walk padding approach and allows denoising of the frequency domain characteristics of the original sequence in an environment that is not affected by noise. Our empirical results show that the proposed denoised approach outperforms random walk padding base denoising in terms of predictive ability and explanatory power with several financial indexes including but not limited to S&P 500, DJI, and TWII.

1. Abu-Mostafa, Y. S. and Atiya, A. F. (1996). Introduction to financial forecasting. Applied Intelligence, 6(3):205–213.

2. Altissimo, F., Bassanetti, A., Cristadoro, R., Forni, M., Hallin, M., Lippi, M., Reichlin, L., and Veronese, G. (2001). Eurocoin: a real time coincident indicator of the euro area business cycle. Available at SSRN 296860.

3. Babu, C. N. and Reddy, B. E. (2014). A moving-average filter based hybrid arima–ann model for forecasting time series data. Applied Soft Computing, 23:27–38.

4. Bahramy, F. and Crone, S. F. (2013). Forecasting foreign exchange rates using support vector regression. In 2013 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr), pages 34–41. IEEE.

5. Baker, M. and Wurgler, J. (2006). Investor sentiment and the cross-section of stock returns. Journal of Finance, 61(4):1645–1680.

6. Bao, W., Yue, J., and Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PloS one, 12(7):e0180944.

7. Baxter, M. and King, R. G. (1999). Measuring business cycles: approximate band-pass filters for economic time series. Review of Economics and Statistics, 81(4):575–593.

8. Berkman, H. and Koch, P. D. (2008). Noise trading and the price formation process. Journal of Empirical Finance, 15(2):232–250.

9. Cao, L. (2003). Support vector machines experts for time series forecasting. Neurocomputing, 51:321–339.

10. Chan Phooi M’ng, J. and Mehralizadeh, M. (2016). Forecasting east asian indices futures via a novel hybrid of wavelet-pca denoising and artificial neural network models. PloS one, 11(6):e0156338.

11. Chen, M.-Y. and Chen, B.-T. (2014). Online fuzzy time series analysis based on entropy discretization and a fast fourier transform. Applied Soft Computing, 14:156–166.

12. Chen, N.-F., Roll, R., and Ross, S. A. (1986). Economic forces and the stock market. Journal of Business, pages 383–403.

13. Christiano, L. J. and Fitzgerald, T. J. (2003). The band pass filter. International Economic Review, 44(2):435–465.

14. Deboeck, G. J. (1994). Trading on the edge: neural, genetic, and fuzzy systems for chaotic financial markets, volume 39. John Wiley & Sons.

15. Dhyani, B., Kumar, M., Verma, P., and Jain, A. (2020). Stock market forecasting technique using arima model. International Journal of Recent Technology and Engineering, 8(6):2694–2697.

16. Dow, J. and Gorton, G. (1997). Noise trading, delegated portfolio management, and economic welfare. Journal of Political Economy, 105(5):1024–1050.

17. Fama, E. F. and French, K. R. (1992). The cross-section of expected stock returns. Journal of Finance, 47(2):427–465.

18. Hall, J. W. (1994). Adaptive selection of us stocks with neural nets. Trading on the edge: neural, genetic, and fuzzy systems for chaotic financial markets. New York: Wiley, pages 45–65.

19. Hassani, H., Dionisio, A., and Ghodsi, M. (2010). The effect of noise reduction in measuring the linear and nonlinear dependency of financial markets. Nonlinear Analysis: Real World Applications, 11(1):492–502.

20. Hodrick, R. J. and Prescott, E. C. (1997). Postwar us business cycles: an empirical investigation. Journal of Money, credit, and Banking, pages 1–16.

21. Krollner, B., Vanstone, B. J., Finnie, G. R., et al. (2010). Financial time series forecasting with machine learning techniques: a survey. In ESANN.

22. Kunsch, H. R. (1989). The jackknife and the bootstrap for general stationary observations. The Annals of Statistics, pages 1217–1241.

23. Larsen, J. I. (2010). Predicting stock prices using technical analysis and machine learning. Norwegian University of Science and Technology.

24. Li, Z. and Tam, V. (2017). Combining the real-time wavelet denoising and long-short-term-memory neural network for predicting stock indexes. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pages 1–8. IEEE.

25. Lim, B. and Zohren, S. (2021). Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A, 379(2194):20200209.

26. Liu, R. Y. (1992). Moving blocks jackknife and bootstrap capture weak dependence. Exploring the limits of bootstrap.

27. Lu, C.-J., Lee, T.-S., and Chiu, C.-C. (2009). Financial time series forecasting using independent component analysis and support vector regression. Decision Support Systems, 47(2):115–125.

28. Politis, D. N. and Romano, J. P. (1994). The stationary bootstrap. Journal of the American Statistical association, 89(428):1303–1313.

29. Raudys, A., Lenˇciauskas, V., and Malˇcius, E. (2013). Moving averages for financial data smoothing. In International conference on information and software technologies, pages 34–45. Springer.

30. Roondiwala, M., Patel, H., and Varma, S. (2017). Predicting stock prices using lstm. International Journal of Science and Research (IJSR), 6(4):1754–1756.

31. Sarode, S., Tolani, H. G., Kak, P., and Lifna, C. (2019). Stock price prediction using machine learning techniques. In 2019 international conference on intelligent sustainable systems (ICISS), pages 177–181. IEEE.

32. Song, D., Baek, A. M. C., and Kim, N. (2021). Forecasting stock market indices using padding-based fourier transform denoising and time series deep learning models. IEEE Access, 9:83786–83796.

33. Srivastava, M., Anderson, C. L., and Freed, J. H. (2016). A new wavelet denoising method for selecting decomposition levels and noise thresholds. IEEE access, 4:3862–3877.

34. Vijh, M., Chandola, D., Tikkiwal, V. A., and Kumar, A. (2020). Stock closing price prediction using machine learning techniques. Procedia Computer Science, 167:599–606.

35. Wang, J.-H., Jiang, J.-H., and Yu, R.-Q. (1996). Robust back propagation algorithm as a chemometric tool to prevent the overfitting to outliers. Chemometrics and Intelligent Laboratory Systems, 34(1):109–115.

36. Xu, S. Y. and Berkely, C. (2014). Stock price forecasting using information from yahoo finance and google trend. UC Brekley.

37. Ying, J., Kuo, L., and Seow, G. S. (2005). Forecasting stock prices using a hierarchical bayesian approach. Journal of Forecasting, 24(1):39–59.

38. Yu, H., Ming, L. J., Sumei, R., and Shuping, Z. (2020). A hybrid model for financial time series forecasting—integration of ewt, arima with the improved abc optimized elm. IEEE Access, 8:84501–84518.

39. Yu, P. and Yan, X. (2020). Stock price prediction based on deep neural networks. Neural Computing and Applications, 32:1609–1628.