Dynamic Prediction and Volatility Analysis of the Hang Seng Index based on the VAR-LSTM Model

Yuchen Dai

doi:10.54691/5e2ac607

Authors

Yuchen Dai

DOI:

https://doi.org/10.54691/5e2ac607

Keywords:

Hang Seng Index; VAR-LSTM Model; Prediction; Volatility Analysis; Macroeconomic Indicators.

Abstract

The Hang Seng Index, as a key index in the Hong Kong financial market, its accurate prediction is of great significance to investors, financial institutions, and policymakers. Given that traditional prediction methods struggle to capture the non-linear characteristics and complex patterns of financial data, this study constructs a VAR-LSTM combined model for predicting the Hang Seng Index. The research selects Hang Seng Index data and multiple macroeconomic indicators over a specific period, screens out key indicators through correlation coefficient analysis, and compares the prediction performances of multiple different LSTM models and the VAR-LSTM model. The results show that the VAR-LSTM model performs remarkably well in fitting data and predicting unknown data, outperforming other models in various error indicators of the training set and the test set. This indicates that the VAR-LSTM combined model has promising prospects in predicting the Hang Seng Index and can provide more accurate prediction information for market participants. However, the financial market is complex and volatile. In the future, it is still necessary to explore methods to optimize the model to further improve the accuracy and reliability of predictions.

Downloads

Download data is not yet available.

References

[1] Mu, L. H., Yu, Q., Yu, Z. X., & Shao, J. C. (2020). Prediction of Coal Prices Based on the Grey Prediction Method. Coal Mine Machinery, 11, 166 - 169.

[2] Kyle, A. S. (1985). Continuous auctions and insider trading. Econometrica: Journal of the Econometric Society, 1315 - 1335.

[3] Nguyen, H. V., Naeem, M. A., Wichitaksorn, N., & Pears, R. (2019). A smart system for short - term price prediction using time series models. Computers & Electrical Engineering, 76, 339 - 352.

[4] Box, G. E., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time series analysis: forecasting and control. John Wiley & Sons.

[5] Zhao, H. (2021). Futures price prediction of agricultural products based on machine learning. Neural Computing and Applications, 33(3), 837 - 850.

[6] Hochreiter, S. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.

[7] Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W. (2021, May). Informer: Beyond efficient transformer for long sequence time - series forecasting. In Proceedings of the AAAI conference on artificial intelligence (Vol. 35, No. 12, pp. 11106 - 11115).

[8] Ren, S. Q., & Song, W. (2024). Feature Extraction of Financial Data and Price Prediction Based on the GGInformer Model. Journal of Zhengzhou University (Natural Science Edition), 56(5), 62 - 70.

[9] Guan, F. X., & Yao, R. K. (2022). Research on the Price Fluctuations of Small - scale Agricultural Products and the Influence of Random Factors - Taking Garlic Prices as an Example. Price: Theory & Practice, (9), 117 - 120 + 206.

[10] Li, J. D., & Li, X. D. (2018). Analysis of the Financialization Factors Affecting the Price Fluctuations of Small - scale Agricultural Products in China - An Empirical Study Based on the Price Data of Garlic and Mung Beans. Journal of Agrotechnical Economics, (8), 98 - 111.

[11] Fu, L. L., Fang, Q., Yuan, D. Y., & Teng, J. M. (2024). Prediction of Pig Prices Based on the Singular Spectrum Decomposition and LSTM - ARIMA Combined Model. Journal of Chinese Agricultural Mechanization, 45(5), 176 - 181 + 252.

[12] Zhu, W. X., Yin, L. T., Liu, D. L., & Xu, L. (2022). Research on the Fluctuation Characteristics and Prediction Method Application of Tungsten Product Prices - Analysis Based on the ARIMA - SVM - LSTM Combined Model. Price: Theory & Practice, (6), 73 - 76 + 192.

[13] Gu, Y. H., Jin, D., Yin, H., Zheng, R., Piao, X., & Yoo, S. J. (2022). Forecasting agricultural commodity prices using dual input attention LSTM. Agriculture, 12(2), 256.

[14] Wang, Y., Liu, P., Zhu, K., Liu, L., Zhang, Y., & Xu, G. (2022). A Garlic - Price - Prediction Approach Based on Combined LSTM and GARCH - Family Model. Applied Sciences, 12(22), 11366.

[15] Guo, Y. C., Jia, H. P., Yu, T., & Liu, D. N. (2023). A Carbon Price Prediction Method Based on the CNN - LSTM Combined Model. Science and Technology Management Research, 43(11), 200 - 206.

[16] Li, H., Hua, J. J., & Zou, B. R. (2022). Stock Price Prediction Based on the RF - LSTM Combined Model. Journal of Henan Polytechnic University (Natural Science Edition), 41(1), 136 - 142.

[17] Song, P., & Zhang, M. (2021). The VAR - LSTM Framework for Predicting Treasury Bond Yields. Statistics & Decision, 37(5), 148 - 152.