Forecast Research on the Fluctuation Risk of Green Financial Market in China based on the GARCH-LSTM Mixed Model

Zhenyu Han

doi:10.54097/hbem.v9i.9233

Authors

Zhenyu Han

DOI:

https://doi.org/10.54097/hbem.v9i.9233

Keywords:

Green Financial Market; Financial Volatility Forecast; GARCH Family Model; LSTM Model; VaR.

Abstract

With the rapid development of China’s green financial market, there is also the problem of uncertain risk of fluctuation in the transaction price of green financial products. Therefore, it is imperative to give play to the role of price fluctuations in early warning of risks in green financial markets. Based on the closing price data of green stock market and green bond market from April 19, 2018 to April 18, 2023, this paper combines the traditional time series model and deep learning model to fit and forecast the yield volatility of green financial market, and quantifies the risk value of green financial market. The results show that: (1) Both the green stock market and the green bond market have the characteristics of leptokurtosis and fat-tail, volatility aggregation and long-term memory to varying degrees. (2) The volatility risk in the green financial market has obvious differentiation characteristics, and the volatility in the green stock market is significantly higher than that in the green bond market. (3) The prediction accuracy of LSTM long-term and short-term memory model is significantly higher than that of GARCH family model. The GARCH-LSTM mixed model can further improve the prediction accuracy. According to the research results, the combination of modern artificial intelligence algorithm and classical econometric theory can become an important means to identify the volatility risk of green financial market, and put forward meaningful suggestions for the risk management of green financial market.

Downloads

Download data is not yet available.

References

Yang Lan. Prediction of Stock Index Volatility Based on LSTM Fusion GARCH Model [D]. Lanzhou University of Finance and Economics, 2021.doi: 10.27732/d.cnki.gnzsx.2021.000228.

Krasnovskiy Evgeny, Nemtchinova Elena, Mityakova Olga, Garnik Sergey, Gasanbekov Sergey, Ten Anatoly, Mardas Dmitry. Estimating the Volatility of Commodity Prices Indices for Agricultural Raw Materials Using the GARCH Model [J]. Indian Journal of Economics and Development, 2023, 18 (3).

Ye Tian. Prediction of Stock Index Volatility Based on GARCH Family Model and LSTM Model [D]. Suzhou University, 2021.doi: 10.27351/d.cnki.gszhu.2021.003756.

Ju Yuhong. Research on the Mechanism and System of Green Economy Development in China [D]. Wuhan University of Technology, 2009.

Tang Chun, Wang Guojing. Research on the Stock Price Effect of Green Index Release: Based on the Perspective of Investor Sentiment [J]. Journal of Business Economics, 2020 (01): 79-91. DOI: 10.14134/j.cnki.cn33-1336/f.2020.01.007.

Shi Jiaqin. Research and Application of Financial Time Series Based on GARCH and Neural Network Model [D]. Zhejiang University of Technology, 2020.doi: 10.27463/d.cnki.gzgyu.2020.001444.

Song Shijia, Li Handong. Predicting VaR for China’s Stock Market: A Score-driven Model Based on Normal Inverse Gaussian Distribution [J]. International Review of Financial Analysis, 2022, 82.

Li Jiantao, Medwin. Green Financial Market System: Theoretical Basis, Status Quo and Factor Expansion [J]. Financial Forum, 2021, 26 (06): 17-26+38. DOI: 10.16529/J. Cnki.11-4613/F.2021.06.003.

Zheng Zhiyong. Study on the Daily Effect of Shanghai Stock Exchange Index Return Rate [D]. Changsha University of Technology, 2017.

Zhao Mingming. Linkage Analysis of Green Bonds, Low-Carbon Industry Stocks and Carbon Emission Rights Market [D]. Lanzhou University, 2021.doi: 10.27204/d.cnki.glzhu.2021.001443.

Labatt, S. & White, R R. Environmental Finance: A Guide to Environmental Risk Assessment and Financial Products [M]. John Wiley and Sons, 2003.

Hu Angang, Zhou Shaojie. Green Development: Functional Definition, Mechanism Analysis and Development Strategy [J]. China Population Resources and Environment, 2014, 24 (01): 14-20.

Meng Xiangyu. Research on China’s Financial Risk Prevention Efforts and Legal System Support [J]. SHS Web of Conferences, 2023, 157.

Antonio Salvi, Emanuele Teti, Anastasia Giakoumelou. The Relationship between LBOs, IPOs and Market Risk Premium: An Empirical Analysis of the European Market [J]. International Journal of Business and Management, 2019, 14 (7).

Liu Yufei. VaR Model and Its Application in Financial Supervision [J]. Economic Science, 1999 (01): 40-51. DOI: 10.19523/J.JJKX.1999.01.006.

Xu Weimin, Xiao Jian. Research on Price Risk Measurement of Carbon Financial Transactions in China: Based on the Perspective of GARCH-VaR Model [J]. Research on Financial Education, 2022, 35 (06): 3-10.

Song Min, Xin Qiang, He Yi-nan. VaR Measurement and Prevention and Control of Market Risk in Carbon Financial Transactions: Based on the Analysis of Five Carbon Emissions Trading Exchanges in China [J]. Journal of Xi 'an University of Finance and Economics, 2020, 33 (03): 120-128. DOI: 10.19331/J.Cnki.JXUFE.2020.03.015.

Liu Hui, Yao Haixiang, Qinghua Ma. An Empirical Study of VaR Historical Simulation under Fluctuation Change [J]. Operation and Management, 2017, 26 (12): 112-118.

Tian Chengshi. Analysis of the Influencing Factors of China Stock Market Risk Based on Conditional VaR Model [J]. Mathematical Practice and Understanding, 2008, 38 (24): 37-43.

Elisa Alòs, Maria Elvira Mancino, Tai-Ho Wang. Quantitative Developments in Financial Volatility: Theory and Practice [J]. Decisions in Economics and Finance, 2019, 42(2).

Yin Liangan, Shao Xidong. Comparative Study on the Forecast Capability of Volatility Models in China Financial Market [J]. Forecast, 2009, 28 (05): 20-26.

Engle R F. Autoregressive Conditional Heteroskedasticity with Estimates of the Variance for U.K. Information [J]. Trans Econometrica, 1982, 50(3): 987-1007.

Bollerslev T. Generalized Autoregressive Conditional Heteroscedasticity [J].Journal of Econometrics, 1986, 31(2): 307-327.

Liu Tong, Shi Yanlin. Innovation of the Component GARCH Model: Simulation Evidence and Application on the Chinese Stock Market [J]. Mathematics, 2022, 10(11).

Chen Xuehui, Zhu Hongli, Zhang Xinru, Zhao Lutao. A novel time-varying FIGARCH model for improving volatility predictions [J]. Physica A: Statistical Mechanics and its Applications, 2022, 589.

Huang Yizhou, Wang Xue. Volatility Forecast: Can Multivariate GARCH Models Overcome Univariate GARCH Models: PK of Binary DCC-GARCH Model and Univariate GARCH Model [J]. Systems Engineering, 2023, 41 (02): 125-134.

Wang Jiani, Li Wenhao. Can GARCH Model Provide Good Volatility Forecast [J]. Quantitative Economic and Technological Economic Research, 2005 (06): 74-87.

Ma Yulin, Wang Xiquan. An Empirical Study on VaR Model Based on Real Volatility [J]. Journal of Shandong University (Science Edition), 2007 (10): 84-89.

Liu Qing, Dai Jingyue, Yang Chao. Performance Evaluation Method of Earnings Volatility Forecast Based on GARCH Family Model [J]. Statistics and Decision, 2015 (09): 160-163. DOI: 10. 13546/ J. Cnki. TJYJC.2015.09.043.

Chen Weihua. Comparative Study on the Forecast Effect of Shanghai Composite Index Volatility Based on Deep Learning [J]. Statistics and Information Forum, 2018, 33 (05): 99-106.

Yu Yan. A Study of Stock Market Predictability Based on Financial Time Series Models [J]. Mobile Information Systems, 2022, 2022.

Wang Yino. Application of GARCH Model and G-VaR in Risk Measurement [D]. Shandong University, 2022.doi: 10.27272/d.cnki.gshdu.2022.002297.

Cai Yuping, Zhang Yuanpeng. Building a Green Financial System: Problems and Solutions [J]. Financial Theory and Practice, 2014 (09): 66-70.

Hu Qingping. Research on the Risk Spillover Effect between Green Bond Market and Green Stock Market [D]. Suzhou University of Science and Technology, 2022.doi: 10.27748/d.cnki.gszkj.2022.000314.

Kakade Kshitij, Mishra Aswini Kumar, Ghate Kshitish, Gupta Shivang. Forecasting Commodity Market Returns Volatility: A Hybrid Ensemble Learning GARCH-LSTM based Approach [J]. Intelligent Systems in Accounting, Finance and Management, 2022, 29 (2).

Gao Tong, Zhu Hailong. Volatility Forecast Based on GARCH Model and BP Neural Network Model: Based on the Daily Data of Shanghai Composite Index [J]. Financial Economy, 2020 (09): 37-45. DOI: 10.14057/j.cnki.cn43-1156/f.2020.09.004.