Author(s)

ZiHang Zeng

Affiliation(s)

School of AI and Advanced Computing, Xi'an Jiaotong-Liverpool University, Suzhou 215400, Jiangsu, China.

Corresponding Author

ZiHang Zeng

ABSTRACT

The realized volatility (RV) in financial time series is characterized by nonlinearity, volatility, and noise. It is challenging to predict RV with a solitary forecasting model for precision. This study employs a hybrid model that integrates the Long Short-Term Memory (LSTM) network with the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) for the purpose of forecasting the returns volatility (RV) of the S&P 500 index, thereby validating its accuracy and robustness.

KEYWORDS

LSTM; CEEMDAN; Realized volatility

CITE THIS PAPER

ZiHang Zeng. Realized volatility prediction with a hybrid model: LSTM-CEEMDAN. Journal of Trends in Financial and Economics. 2024, 1(1): 13-19. DOI: 10.61784/jtfe3005.

REFERENCES

[1] Singh R, Srivastava S. Stock prediction using deep learning. Multimedia Tools and Applications, 2017, 76: 18569-18584. 

[2] Bhattacharjee I, Bhattacharja P. Stock price prediction: a comparative study between traditional statistical approach and machine learning approach. 2019 4th international conference on electrical information and communication technology (EICT), 2019: 1-6

[3] Ariyo AA, Adewumi AO, Ayo CK. Stock price prediction using the ARIMA model. 2014 UKSim-AMSS 16th international conference on computer modelling and simulation, 2014: 106-112.

[4] Cortes C, Vapnik V. Support-vector networks. Mach Learn, 1995, 20: 273–97.

[5] Suykens JA, Van Gestel T, De Brabanter J, De Moor B, Vandewalle JP. Least squares support vector machines. World scientific, 2002.

[6] Zhu BZ, Wei YM. Carbon price prediction based on integration of GMDH, particle swarm optimization and least squares support vector machines. Syst Eng-Theory Pract, 2011, 31(12): 2264–71.

[7] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553): 436–44

[8] Yah?i M, ?anako?lu E, A?ral? S. Carbon price forecasting models based on big data analytics. Carbon Manage, 2019, 10(2):175–87.

[9] Holthausen RW, Larcker DF. The prediction of stock returns using financial statement information. Journal of accounting and economics, 1992, 15(2-3): 373-411.

[10] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput, 1997, 9(8): 1735–80.

[11] Zhang Z. Research on stock index prediction based on ARIMA-CNN-LSTM model. 9th International Conference on Financial Innovation and Economic Development (ICFIED 2024), 2024, 558-565.

[12] Daubechies I. Ten lectures on wavelets. Society for industrial and applied mathematics, 1992.

[13] Huang NE, Shen Z, Long SR, et al. The empirical mode decomposition and the Hilbert spectrum for non-linear and nonstationary time series analysis. Proc R Soc Lond Ser A Math Phys Eng Sci, 1998, 454(1971): 903–95.

[14] Wu Z, Huang NE. Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal, 2009, 1(01): 1–41.

[15] Yeh JR, Shieh JS, Huang NE. Complementary ensemble empirical mode decomposition: A novel noise enhanced data analysis method. Adv Adapt Data Anal, 2010, 2(02): 135–56.

[16] Torres ME, Colominas MA, Schlotthauer G, Flandrin P. A complete ensemble empirical mode decomposition with adaptive noise. In: 2011 IEEE international conference on acoustics, speech, and signal processing (ICASSP). , 2011, 4144–7.

[17] Dragomiretskiy K, Zosso D. Variational mode decomposition. IEEE Trans Signal Process, 2013, 62(3): 531–44.