基于定单流的证券投资策略研究

发布时间：2018-05-05 15:12

本文选题：金融市场微观结构理论 + 定单流　；参考：《电子科技大学》2012年博士论文

【摘要】：Markowitz和Tobin提出均值-方差模型，标志着现代证券投资组合理论发展的开端。从此，各国学者对均值-方差模型进行了深入的研究，以均值-方差模型为基础建立了不同的投资组合，提出了不同的投资策略。另一方面，金融市场微观结构理论的发展，为证券投资组合理论的发展提供了新的发展方向。作为市场微观结构理论的一个核心变量——定单流，不仅具有明确、直观的涵义，而且能够刻画资金的流向，具有丰富的信息含量，反映了投资者的投资组合再平衡行为。因此，本文利用定单流刻画资金的流向，选择投资股票和板块，构建基于定单流的证券投资策略，分析投资策略的风险，为证券投资者的投资策略提供参考，指导投资者的投资决策。首先，本文引入定单流刻画资金的净流入和净流出，根据资金的流向选择股票和板块，提出了基于定单流的股票和板块选择方法。采用事件研究法分析了证券分析师推荐股票和板块的总体特征。根据这些特征，采用朴素贝叶斯分类（NaiveBayes Classifier，简称NBC）方法分别将深证成指指数股票和所有板块分为符合这些特征的股票和板块以及不符合这些特征的股票和板块，筛选出符合这些特征的股票和板块，计算其收益率，并与证券分析师推荐的股票和板块收益率以及深证成指指数收益率进行比较分析。实证结果显示，基于定单流的股票和板块选择方法获得的收益率比分析师推荐的股票和板块收益率更高，也比指数的收益率更高，并能获得显著的超额收益率。其次，本文将定单流引入证券投资策略的构建中，提出了基于定单流的静态投资策略。从投资者期望效用最大化角度，将定单流引入投资组合模型，根据定单流指标确定组合权重，构建基于定单流的证券投资组合模型。在只含有风险资产以及同时含有风险资产和无风险资产两种情况下，通过数学推导，得到基于定单流的证券投资组合模型的最优投资权重。在此基础上，提出基于定单流的静态投资策略，根据定单流指标确定投资策略的最优权重。选取深市A股前30只股票进行实证分析，结果表明根据定单流指标确定投资权重，能取得比均值-方差模型和市场指数更高的投资收益。再次，考虑多个投资时期，从投资者期望效用最大化角度，引入定单流指标建立含有交易成本的多期动态投资组合模型。在各个投资时期，根据定单流冲击系数动态调整组合权重。采用数学推导求解动态组合投资模型的最优权重。然后，提出基于定单流的动态投资策略，根据定单冲击系数动态调整投资策略的投资权重。选取深市A股前30只股票进行实证分析，结果表明基于定单流的动态投资策略不仅能跑赢市场指数，而且能获得比均值-方差投资组合更好的投资收益。最后，本文分析了基于定单流的证券投资策略的风险。基于定单流，提出定单冲击系数，，构建定单冲击系数与收益率的二元GARCH模型，检验定单冲击系数与收益率之间的波动溢出效应。在此基础上，根据定单冲击系数的波动分析收益率的波动，分析基于定单流的证券投资策略的风险。将深证综指指数股票分为高定单冲击系数组合与低定单冲击系数组合，比较不同定单冲击系数组合的风险，并进行评价。结果表明，收益率与定单冲击系数之间存在双向波动溢出效应；高定单冲击系数组合的收益率比低定单冲击系数组合更高，但是其风险也更大，说明本文构建的基于定单流的证券投资策略在获得高收益的同时，也承担着高风险。评价结果显示，与低定单冲击系数投资组合相比，高定单冲击系数投资组合能获得更高的风险溢价。
[Abstract]:This paper studies the mean - variance model based on the mean - variance model , and provides a new direction for the development of portfolio theory .

First , the paper introduces the net inflow and net outflow of the order flow , and selects stock and plate according to the flow direction of the funds . The stock and the plate based on the order flow are analyzed . According to these characteristics , the stock and the plate which meet these characteristics are divided into shares and plates which meet these characteristics and the yield of stock and plate which does not meet these characteristics . The empirical results show that the yield of the stock and plate based on the order flow is higher than that of the stock and plate recommended by the analyst and the yield of the index is higher , which is also higher than the yield of the index .

Secondly , in the construction of portfolio investment strategy , this paper puts forward a static investment strategy based on the order flow . Based on this , a portfolio model of portfolio investment based on single flow is proposed . Based on the qualitative analysis , the optimal weight of portfolio model based on order flow is obtained .

A dynamic investment strategy based on the order flow is proposed to solve the dynamic portfolio investment model . The results show that the dynamic investment strategy based on the order flow can not only win the market index but also get better investment income than the mean - variance portfolio .

At last , this paper analyzes the risk of portfolio investment strategy based on the order flow . Based on the order flow , this paper puts forward a two - dimensional model of the impact coefficient of the order and the ratio of the impact coefficient and the yield of the order . On the basis of this , the risk of the portfolio investment strategy based on the order flow is analyzed according to the fluctuation of the impact coefficient of the order .
The combination of the high order impact coefficient combination is higher than the low order impact coefficient combination , but the risk is also greater . It is stated that the portfolio investment strategy based on the order flow constructed in this paper is also responsible for the high risk . The evaluation result shows that compared with the low order impact coefficient investment portfolio , the high order impact coefficient portfolio can obtain higher risk premium .

【学位授予单位】：电子科技大学
【学位级别】：博士
【学位授予年份】：2012
【分类号】：F832.51;F224

【相似文献】