摘要
近年来我国金融市场的迅猛发展,为投资者提供便利的同时也带来了挑战,如何有效地进行资产配置是投资者需要解决的难题之一.Black-Litterman模型不仅解决了传统均值方差模型对参数敏感的问题,而且允许投资者在模型中加入投资观点,是备受关注的资产配置模型.然而,投资者可能会因为自身经验不足而无法给出合适的投资观点,无法发挥模型的应用价值.本文采用基于长短期记忆(LSTM)神经网络表达量化观点的方式为投资者提供了一种解决方案.作为数值算例,本文以申万一级行业指数作为资产池构建投资组合,算例结果表明,与其他参照模型的表现相比,本文构建的资产配置模型有更高的夏普比率和年化收益率.
The rapid development of China’s financial market in recent years has brought not only convenience but also challenges to investors.How to effectively allocate assets is one of the problems that investors need to solve.The Black-Litterman model not only solves the traditional mean variance model parameter-sensitive issues,but also allows investors to add investment perspectives to the model.It is a closely watched asset allocation model.However,investors may not be able to give a suitable investment perspective because of their inexperience,they cannot play the application value of the model.This article uses a long-term short-term memory(LSTM)neural network to express quantitative views to solve this problem.As a numerical example,we use ShenWan first-level industry index as an asset pool to build a portfolio,the result of the example shows that the asset allocation model constructed in this paper has a higher Sharpe ratio and annualized rate of return than other reference models.
作者
李宗铭
房勇
LI Zongming;FANG Yong(Academy of Mathematics and Systems Science,Chinese Academy of Sciences,Beijing 100190,China;School of Economics and Management,University of Chinese Academy of Sciences,Beijing 100190,China)
出处
《系统工程理论与实践》
EI
CSSCI
CSCD
北大核心
2021年第8期2045-2055,共11页
Systems Engineering-Theory & Practice
基金
国家自然科学基金(71631008)。
