基于风险网络结构的资产分配策略研究

doi:10.12005/orms.2021.0160

运筹与管理 ›› 2021, Vol. 30 ›› Issue (5): 161-167.DOI: 10.12005/orms.2021.0160

基于风险网络结构的资产分配策略研究

张伟平¹, 庄新田², 吴冬梅²

1.山东大学经济学院,山东济南 250100;
2.东北大学工商管理学院,辽宁沈阳 110169

收稿日期:2019-08-05 出版日期:2021-05-25
作者简介:张伟平(1990-),女,山东潍坊人,博士后,金融复杂网络;庄新田(1956-),男,吉林四平人,教授,博士生导师,金融复杂网络,供应链金融。
基金资助:
国家自然科学基金资助重点项目(71671030,71571038,71971048)

Research on Asset Allocation Strategy Based on Risk Network Structure

ZHANG Wei-ping¹, ZHUANG Xin-tian², WU Dong-mei²

1. School of Economics, Shandong University, Shandong 250100, China;
2. School of Business Administration, Northeastern University, Shenyang 110169, China

Received:2019-08-05 Online:2021-05-25

摘要/Abstract

摘要： 股票市场是一个高风险市场,如何在频繁发生的极端波动环境下进行有效的资产分配是当前热点问题。本文首次应用VaR模型构建股市风险网络,并基于风险网络模型进行最优投资组合成分选择,分析不同市场波动行情下最优资产分配权重和股票中心性的时变关系,融合风险网络时变中心性和个股表现提出新的动态资产分配策略(φ投资策略)。结果表明:在股市上涨和震荡期,股票中心性和最优投资组合权重呈正相关关系;股市下跌期,股票中心性和最优投资组合权重呈负相关关系;当φ>0.05时,投资者的合理投资区域向高中心性节点移动,反之。φ投资策略的绩效表现证明了风险网络结构能提高投资组合选择过程。此研究对于优化资产配置、提高投资收益、多元化分散投资风险具有重要意义。

关键词: VaR模型, 风险网络, 网络中心性, 最优投资权重, φ投资策略

Abstract: The stock market is a high-risk market, and how to carry out effective asset allocation is a hot issue in the frequent extreme fluctuation environment. This paper first uses VaR (value at risk) model to build stock market risk network, and conducts selection of optimal portfolio by risk network structure. The paper empirically analyzes the time-varying relationship between the optimal asset allocation weight and the risk network centrality under different volatility markets, then proposes a new dynamic portfolio strategy (φ investment strategy) which fuses time-varying central and individual performance. The results show that: there is a positive correlation between the network centrality and the optimal portfolio weight in bull and stable market, and the network centrality and the optimal portfolio weight are negatively correlated in decline market; When φ>0.05, the investor's reasonable investment area moves to the high-central node, otherwise. Finally, the portfolio performance of φ strategy proves that risk network structure can improve the portfolio selection process. This study is of great significance for optimizing allocation of assets, improving the return of investment and diversifying the risk of investment.

Key words: VaR model, risk network, network centrality, optimal portfolio weight, φ investment strategy

中图分类号:

F830

张伟平, 庄新田, 吴冬梅. 基于风险网络结构的资产分配策略研究[J]. 运筹与管理, 2021, 30(5): 161-167.

ZHANG Wei-ping, ZHUANG Xin-tian, WU Dong-mei. Research on Asset Allocation Strategy Based on Risk Network Structure[J]. Operations Research and Management Science, 2021, 30(5): 161-167.

参考文献

[1] 刘勇军,张卫国,徐维军.考虑现实约束的模糊多准则投资组合优化模型[J].系统工程理论与实践,2013,33(10):2462-2470.
[2] 许启发,周莹莹,蒋翠侠.带有范数约束的CVaR高维组合投资决策[J].中国管理科学,2017,25(2):40-49.
[3] Nazemi A, Abbasi B, Omidi F. Solving portfolio models with uncertain returns using an artificial neural network scheme[J]. Appl Intell. 2015, 42: 609-621.
[4] Hassan M R, Ramamohanarao K, Kamruzzaman J. A HMM-based adaptive fuzzy inference system for stock market forecasting[J]. Neurocomputing, 2013, 104: 10-25.
[5] Jigap P, Sahil S, Priyank T. Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques[J]. Exp. Sys. Applic, 2015, 42(1): 259-268.
[6] 黄玮强,王丹,庄新田,姚爽.我国股票关联网络弹性与市场运行的互动关系[J].系统工程,2017,35(2):1-7.
[7] 王占浩,郭菊娥,薛勇.资产负债表关联、价格关联与银行间风险传染[J].管理工程学报,2016,2(30):202-210.
[8] Boginski V, Butenko B, Shirokikh O, et al. A network-based data mining approach to portfolio selection via weighted clique relaxation[J]. Ann Oper Res, 2014, 216(1): 23-34.
[9] Choudury S, Ghosh S, Bhattacharya A, et al. A real time clustering and SVM based price-volatility prediction for optimal trading strategy[J]. Neuro., 2014, 89(3): 0228-0237.
[10] Pozzi F, DI Matteo T, Aste T. Spread of risk across financial markets: better to invest in the peripheries[J]. Scientific Reports, 2013, 24(3): 1665-1674.
[11] Yan L, Xiong F J, Yue T, et al. Portfolio optimization based on network topology[J]. Physica A, 2019, 515: 671-681.
[12] Ren F, Lu Y, LI S, et al. Dynamic portfolio strategy using clustering approach[J]. Plos One, 2017, 12(1): 1371-1380.
[13] 袁铭.基于多标度曲线的股市网络构造及社区挖掘[J].计算机工程,2015,41(4):60-65.
[14] 钟韬,彭勤科.基于社会网络分析的投资组合优选方法[J].系统工程理论与实践,2015,35(12):3017-3025.
[15] 黄玮强,庄新田,姚爽.复杂网络视角下的我国股票之间信息溢出研究[J].运筹与管理,2013,22(5):177-184.
[16] Rockfellar R, Uryasev S. Optimization of conditional Value-at-Risk[J]. Journal of Risk, 2000, 3(2): 21-42.
[17] Gong P, Weng Y. Value-at-risk forecasts by a spatiotemporal model in Chinese stock market[J]. Physica A, 2016, 441: 173-191.
[18] Ledoit O, Wolf M. Robust performance hypothesis testing with the variance[J]. Wilmott, 2011, 55(6): 86-89.

基于风险网络结构的资产分配策略研究

Research on Asset Allocation Strategy Based on Risk Network Structure

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

[1]	张茂军, 李昊, 南江霞, 王国栋. 银行间与交易所国债市场的信息溢出效应研究[J]. 运筹与管理, 2021, 30(12): 165-171.
[2]	李延双, 庄新田, 张伟平. 股指极端波动下中国股市复杂网络结构及中心性分析[J]. 运筹与管理, 2020, 29(7): 131-143.
[3]	郝英. 养老保险与经济增长关系的研究——以内蒙古自治区为例[J]. 运筹与管理, 2020, 29(5): 218-226.
[4]	王苏生, 李光路, 王俊博. 沪深300股指期货日内绝对收益率与成交量之间动态关系研究[J]. 运筹与管理, 2020, 29(2): 166-174.
[5]	张伟平, 庄新田, 吴冬梅. 我国股市网络稳定性及其宏观影响因素——基于三种网络拓扑结构、鲁棒性的实证研究[J]. 运筹与管理, 2020, 29(1): 185-194.
[6]	黄玮强, 郭慧敏, 姚爽. 尾部风险网络视角下的金融机构系统性风险贡献研究[J]. 运筹与管理, 2019, 28(3): 118-126.
[7]	谌金宇,朱学红. 产业链视角下结构性有色金属价格冲击的行业传导效应[J]. 运筹与管理, 2018, 27(11): 95-104.
[8]	吴亚军, 惠晓峰. 基于均线交易系统的非特定时间动态VaR研究[J]. 运筹与管理, 2013, 22(6): 177-183.