基于EEMD-LSTM的中国保险业系统性风险预警研究

管理评论 ›› 2022, Vol. 34 ›› Issue (9): 27-34.

基于EEMD-LSTM的中国保险业系统性风险预警研究

唐振鹏, 吴俊传, 张婷婷, 陈凯杰

福州大学经济与管理学院, 福州 350108

收稿日期:2019-08-26 出版日期:2022-09-28 发布日期:2022-10-28
通讯作者: 吴俊传(通讯作者),福州大学经济与管理学院博士研究生
作者简介:唐振鹏,福州大学经济与管理学院院长,教授,博士生导师;张婷婷,福州大学经济与管理学院博士研究生;陈凯杰,福州大学经济与管理学院硕士研究生。
基金资助:
国家自然科学基金项目（71573042；71973028）。

An EEMD-LSTM Model Based Research on Early Warning of the Systematic Risk in China Insurance Industry

Tang Zhenpeng, Wu Junchuan, Zhang Tingting, Chen Kaijie

College of Economics and Management, Fuzhou University, Fuzhou 350108

Received:2019-08-26 Online:2022-09-28 Published:2022-10-28

摘要/Abstract

摘要： 本文采用保险业压力指数来衡量中国保险业系统性风险状况，并通过预测保险业压力指数的未来走势来进行保险业系统性风险预警。借鉴TEI@I复杂系统研究方法论中的分解集成技术，同时结合当前人工智能、深度学习领域的研究成果，构建EEMD-LSTM模型进行保险业系统性风险预警。实证结果表明，EEMD分解集成技术在预测非线性、非平稳复杂时间序列方面具有明显优势；同时，LSTM模型能有效刻画时间序列之间的相依、长记忆特性。EEMD-LSTM模型组合预测精度优于其他模型。

关键词: 保险业, 系统性风险, 预警, 集合经验模态分解, 长短期记忆神经网络

Abstract: This paper constructs an insurance industry stress index to measure the systemic risk of China’s insurance industry, and predicts the future risks of the insurance industry by predicting the future trend of the insurance industry’s stress index. Drawing on the EEMD decomposition integration technology in the TEI@I complex system research methodology, combined with the current research results in the field of artificial intelligence and deep learning, the EEMD-LSTM model is constructed to carry out the systemic risk warning of the insurance industry. The empirical results show that EEMD decomposition integration technology has obvious advantages in predicting nonlinear and non-stationary complex time series. At the same time, LSTM model can effectively describe the dependence and long memory characteristics between time series. The EEMD-LSTM model combination prediction accuracy is superior to other models.

Key words: insurance, systemic risk, early warning, ensemble empirical mode decomposition, long short-term memory neural network

唐振鹏, 吴俊传, 张婷婷, 陈凯杰. 基于EEMD-LSTM的中国保险业系统性风险预警研究[J]. 管理评论, 2022, 34(9): 27-34.

Tang Zhenpeng, Wu Junchuan, Zhang Tingting, Chen Kaijie. An EEMD-LSTM Model Based Research on Early Warning of the Systematic Risk in China Insurance Industry[J]. Management Review, 2022, 34(9): 27-34.

参考文献

[1] 郑苏晋,乔恒,蒙羞叶. 保险业服务经济增长:路径及影响机制——多种时间序列模型和基于EGLS的bootstrap检验[J]. 管理评论, 2019,31(6):14-22
[2] Geneva Association. Systemic Risk in Insurance-An Analysis of Insurance and Financial Stability[R]. Report of the Geneva Association Systemic Risk Working Group, 2010
[3] 中国保监会. 国内系统重要性保险机构监管暂行办法(第二轮征求意见稿)[Z]. 2016
[4] BIS, FSB, IMF. Guidance to Assess the Systemic Important of Financial Institutions, Markets and Instruments: Initial Considerations[R]. BIS Meeting, 2009
[5] Zhu B., Li L., Zhou Y., et al. How does Information Disclosure Affect Bank Systemic Risk in the Presence of a Deposit Insurance System?[J]. Emerging Markets Finance and Trade, 2019,55(11):2497-2522
[6] Caporin M., Kolokolov A., Renò R. Systemic Co-Jumps[J]. Journal of Financial Economics, 2017,126:563-591
[7] Frankel J. A., Rose A. K. Currency Crashes in Emerging Markets: An Empirical Treatment[J]. Journal of International Economics, 1996,41:351-366
[8] Sachs J. D., Tornell A., Velasco A., et al. Financial Crises in Emerging Markets: The Lessons from 1995[J]. Brookings Papers on Economic Activity, 1996,1:147-215
[9] Kaminsky G., Lizondo S., Reinhart C. M. Leading Indicators of Currency Crises[R]. MPRA Paper, 1998
[10] Berg A., Coke R. Auto Correlation-Corrected Standard Errors in Panel Probits: An Application to Currency Crisis Prediction[R]. IMF Working Paper, 2004
[11] Illing M., Liu Y. An Index of Financial Stress for Canada[R]. Staff Working Papers, 2003
[12] 徐国祥,李波. 中国金融压力指数的构建及动态传导效应研究[J]. 统计研究, 2017,34(4):59-71
[13] Lall S., Cardarelli R., Elekdag S. Financial Stress, Downturns, and Recoveries[R]. IMF Working Papers, 2013
[14] Duca M. L., Peltonen T. A. Assessing Systemic Risks and Predicting Systemic Events[J]. Journal of Banking & Finance, 2013,37(7):2183-2195
[15] Monin P. J. The OFR Financial Stress Index[J]. Risks, 2019,7(1):1-21
[16] 严一锋,李连发. 基于日度数据的金融压力指数构建[J]. 郑州大学学报(哲学社会科学版), 2017,50(5):49-56
[17] 王培辉,康书生. 中国金融压力周期特征及实时监测——基于混频Markov动态因素模型的研究[J]. 经济学家, 2017,(10):79-87
[18] 刘晓星,方磊. 金融压力指数构建及其有效性检验——基于中国数据的实证分析[J]. 管理工程学报, 2012,26(3):1-6
[19] 郑桂环,徐红芬,刘小辉. 金融压力指数的构建及应用[J]. 金融发展评论, 2014,(8):50-62
[20] 王帅,汤铃,余乐安. 基于单变量分解集成的牛奶消费需求预测研究[J]. 系统科学与数学, 2013,33(1):11-19
[21] Elman J. L. Finding Structure in Time[J]. Cognitive Science, 1990,14(2):179-211
[22] Greff K., Srivastava R. K., Koutnik J., et al. LSTM: A Search Space Odyssey[J]. IEEE Transactions on Neural Networks & Learning Systems, 2015,28(10):2222-2232
[23] Gers F. A. Learning to Forget: Continual Prediction with LSTM[J]. Neural Computation, 2000,12(10):2451-2471
[24] Wang S. Y., Yu L. A., Lai K. K. Crude Oil Price Forecasting with TEI@I Methodology[J]. Journal of Systems Science and Complexity, 2005,18(2):145-166
[25] 汪寿阳,余乐安,黎建强. TEI@I方法论及其在外汇汇率预测中的应用[J]. 管理学报, 2007,4(1):21-27
[26] Walczak B., Massart D. L. Noise Suppression and Signal Compression Using the Wavelet Packet Transform[J]. Chemometrics and Intelligent Laboratory Systems, 1997,36(2):81-94
[27] Huang N. E., Shen Z., Long S. R., et al. The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Nonstationary Time Series Analysis[J]. Proceedings of the Royal Society A, 1998,454(1971):903-995
[28] Wu Z., Huang N. E. A Study of the Characteristics of White Noise Using the Empirical Mode Decomposition Method[J]. Proceedings of the Royal Society A, 2004,460(2046):1597-1611