RECURRENT NEURAL NETWORK-BASED PORTFOLIO INVESTMENT

Instead of existing methods,a recurrent neural network is conceived to deal with three stages of portfolio management.Mainly,a deterministic annealing neural network is proposed for the approach to portfolio problem,which is a kind of quadratic programming.Finally,through a real example,we verify that the neural network model proposed in this paper is a good tool to solve the portfolio problem.

Application of Portfolio Model in the Real Investment Transactions

This paper studies discrete investment portfolio model that the objective function is utility function. According to a hybrid branch-and-bound method based on Lagrangian relaxation and continuous relaxation, the paper analyzes the question using the real statistical data. The results indicate that discrete investment portfolio model really has its guidance in the actual investment.

A dynamic decision model for portfolio investment and assets management

This paper addresses a dynamic portfolio investment problem. It discusses how we can dynamically choose candidate assets, achieve the possible maximum revenue and reduce the risk to the minimum level. The paper generalizes Markowitz’s portfolio selection theory and Sharpe’s rule for investment decision. An analytical solution is presented to show how an institu- tional or individual investor can combine Markowitz’s portfolio selection theory, generalized Sharpe’s rule and Value-at-Risk (VaR) to find candidate assets and optimal level of position sizes for investment (dis-investment). The result shows that the gen- eralized Markowitz’s portfolio selection theory and generalized Sharpe’s rule improve decision making for investment.

Goal Programming for Investment Portfolio and Its Application

To solve the problem of investment portfolio with single goal of maximal NPV, a 0- 1 programming model was proposed and proved effective; and to solve that concerning more elements of a project such as risk level and social benefit, a goal programming model is then introduced. The latter is a linear programming model adopting slack variable called deviation variable to turn inequation constraint into equation constraint, introducing a priority factor to denote different importance of the goals. A case study has demonstrated that this goal programming model can give different results according to different priority requirement of each objective.

Visualizing Investment Decision on Decision Balls

Decision makers’ choices are often influenced by visual background information. This study uses open-ended equity funds in Taiwan to investigate three well-known optimal portfolio models, including the mean-variance, maximin, and minimization of mean absolute deviation. The optimal portfolios are then visualized on Decision Balls to assist investors in making investment decisions. By observing the Decision Balls, investors can see the optimal portfolios, compare the optimal weights provided by the different models, view the cluster of funds, and even find substitute funds if preferred funds are not available.

Value investing or investing in illiquidity?The profitability of contrarian investment strategies, revisited

Background:We investigate whether the success of contrarian investment strategies can be attributed to differences in the relative illiquidity of stocks categorized as value investments versus those categorized as glamour portfolios.Methods:Following Lakonishok et al.(J Financ 49:1541–1578,1994),we assess the illiquidity characteristics of portfolios that underlie contrarian investment strategies that are based on the level of stock’s book to market.Results:We find strong evidence that those portfolios characterized as value investments are associated with dramatically greater levels of illiquidity than glamour portfolios.We further demonstrate that strategies based on the illiquidity in the year prior to portfolio formation result in return characteristic of ostensibly contrarian strategies.Conclusions:These results suggest that the higher returns associated with contrarian investment strategies are the result of the higher illiquidity associated with value portfolios and represent compensation that the investor receives for accepting illiquidity.They also suggest that researchers should be cautious before attributing apparent anomalies to behavior-driven expectational errors rather than to other attributes unrelated to behavior,such as illiquidity.

Investment Strategy of the Temasek Holdings

Sovereign Wealth Funds （SWFs） are generally known as investment funds owned by national governments and financed by the country＇s foreign currency reserves （dollar, euro, and yen）, often through their central banks or via direct investments. The study investigated the investment strategy of the Temasek Holdings as one of the most successful SWFs which is owned by the government of Singapore. Temasek Holdings was founded in 1974 to manage part of the government＇s revenues. Present turbulent times create a big pressure on healthy investment strategy of the SWFs. But total shareholder return for Temasek since its inception in 1974 has been a healthy 17% compounded annually. The main objective of the paper is to focus on the role of the Temasek Holdings as a company managed on commercial principles with an aim to achieve long-term sustainable returns. The study also analyzed Temasek Holdings＇investment strategy. The study provides answers to questions like： why Temasek is of the most successful SWFs and what is the fund risk management？ Another part of the paper compares investment strategy of the Temasek Holdings with other SWFs. The study has been conducted mainly on the basis of literature survey, secondary information and with using various web sites and research paper. The analysis has been also based on disclosures appearing in the Temasek annual reports over the period from 2008 to 2010.

QFII in China Security Market： Status Quo and Investment Strategy

This paper firstly introduces the definition and features of QFII, and then mainly analyzes the QFII＇s portfolio performance and investment yield, as welt as stock market. And at last, it refers to the impacts of QFII＇s companies and supervision systems in China security market. the investment ideas and strategies of QFII in China investment styles and strategies on investors, listed

Turnover Based Illiquidity Measurement as Investment Strategy on Zagreb Stock Exchange

This paper deals with illiquidity measurement of stocks on Croatian Stock market. Illiquidity measures used in this paper are daily ratio of absolute stock return to its dollar volume (ILLIQ) and RCT (Relative change in turnover). Aim of this paper is to show that illiquidity measure RCT makes clear distinction between liquid and illiquid stocks that should be reflected through investment strategy where investment in RCT based illiquid portfolios outperforms investment in ILLIQ based portfolios and CROBEX index. Research was carried out on eighteen stocks from Zagreb Stock Exchange (ZSE) which are constituents of CROBEX index. Portfolios of liquid and portfolios of illiquid stocks based on results of illiquidity measurement were constructed. Behaviour in terms of return and volatility of these portfolios in following one-year period was observed. Results showed that portfolios formed using RCT as measure of illiquidity constantly outperformed CROBEX index and ILLIQ based portfolios. Returns of RCT based portfolios had lower standard deviation and were more stable than ILLIQ based portfolios in whole period. RCT as a measure of illiquidity produces valuable information on stock liquidity that can be exploited as investment strategy reflecting itself in larger expected returns of RCT portfolios in future period than expected returns of ILLIQ based portfolios and market.

考虑乡村振兴贡献度的农网项目投资决策模型

深入推进乡村振兴战略对农村电网发展提出更高要求,量化新时代农网项目贡献度,辅助农网实现精准投资成为关键。基于乡村振兴战略对现代农村电网发展提出的新要求,构建包含安全可靠、精准服务、绿色低碳、数字智能等4个维度的农网贡献度评价指标体系,采用最小交叉熵模型融合完全一致性方法(FUCOM)-变异系数法赋权系数对指标进行组合赋权,运用加权马氏距离TOPSIS法量化农网贡献度。以农网单位投资贡献度最优及财务效益最大为目标,构建农网项目投资决策模型,并基于c-DPEA算法进行求解。某县某批次20个农网项目的算例仿真结果表明,所提量化模型能科学评价农网项目贡献度,投资决策模型能为农网实现精准投资提供有效参考。

健康投资对家庭资产组合有效性的影响研究

健康作为一种典型的背景风险,对家庭的投融资决策有重要影响。基于2019年中国家庭金融调查(CHFS)数据,文章使用普通最小二乘法(OLS)和两阶段最小二乘法(2SLS)研究了健康投资对家庭资产组合有效性的影响。研究发现:健康投资能显著提升家庭资产组合有效性且结果具有较好的稳健性;健康投资会通过影响居民主客观金融素养水平和家庭收入水平从而影响家庭资产组合有效性;健康投资对城镇家庭、东部地区家庭、中高教育水平家庭的资产组合有效性的影响更大。该研究为健康投资如何影响家庭财富提供了重要的理论依据和政策含义。

离岸金融中心的系统性金融风险与离岸证券投资——兼论金融监管的作用

离岸金融中心(OFCs)囤积着巨额离岸证券投资但也隐藏着系统性金融风险。文章采用36个OFCs的2006-2020年面板数据,合成并测度了全球OFCs的系统性金融风险,并以此检验了其与OPI的关系和金融监管在其间发挥的作用。研究发现,全球离岸金融系统性风险呈现下降趋势,其中银行市场、货币市场和外汇市场贡献度较高,并且系统性风险抑制了离岸投资者持有OPI。国际社会重压下的离岸金融监管并非力有不逮,而是通过降低金融市场和政府部门风险两条路径降低系统性金融风险,进而吸引了OPI。异质性研究表明,金融监管抑制股权类OPI风险的效果比债务类OPI更为显著,对OPI风险的遏制作用则在金融危机后比危机前更加突出。

基于投资组合高阶矩分析的电力系统灵活性评估

针对现有灵活性指标形式主要集中于低阶统计量,仅能反映系统灵活性的平均水平与集中程度,而忽视了灵活性的高阶特征这一问题,引入投资组合高阶矩分析理论对电力系统灵活性进行刻画,以揭示系统灵活性的调节潜力与风险。首先,通过分析投资组合的均值-方差-偏度-峰度模型(mean-variance-skewness-kurtosismodel,MVSK Model),给出了灵活性单元组合的定义,基于多元Copula函数构建考虑空间相关性的灵活性单元概率模型。其次,基于灵活性单元组合的各阶矩建立灵活性评估指标,并给出基于核密度估计与蒙特卡洛模拟的指标计算方法。最后,通过FTS-213测试系统与德国某电网的历史数据对所提指标进行了测算和验证。算例表明所提指标能够反映系统灵活性调节能力的平均水平、稳定程度、潜力与风险,且能量化评估灵活性资源种类与投建地区对系统灵活性的影响,为后续的灵活性资源规划提供理论支持。

一种新的混合共轭梯度法及其在投资组合中的应用

考虑无约束优化问题,在不同维数的空间上获得具有充分下降性的搜索方向,进而提出一个新的混合共轭梯度方法,在梯度Lipschitz连续条件下,证明了算法的全局收敛性。数值实验表明,该算法具有一定竞争力,将该方法应用于求解Markowitz投资组合问题,得到不同收益率下的投资组合策略。

考虑投资不确定性的项目组合选择IGDT模型

受政策的改变以及对新兴领域项目投资缺少足够认知的影响,管理者的项目投资行为往往呈现一定的不确定性。针对企业管理者在进行项目组合投资决策时存在一定风险偏好的情况,本文基于信息间隙决策理论(Information Gap Decision Theory,IGDT),引入净现值偏差系数对管理者的风险偏好进行描述,构建了考虑投资不确定性的项目组合选择新模型。采用包络约束对投资金额不确定性进行描述,给出风险规避与机会寻求两种策略下的项目组合选择IGDT优化模型,并将其转化成单层规划模型进行求解。通过算例仿真,验证了模型的有效性。结果表明:IGDT优化模型不仅满足了管理者投资的预期净现值要求,而且给出了最优的投资金额与项目选择结果。本文构建模型可以为管理者在项目风险管控和资金管理优化方面提供参考。

基于TSO-LSTM神经网络的股票收益率均值预测模型及其在智能投资中的应用

根据股票收益的历史数据,建立数据和模型双驱动的智能资产配置系统,指导股民投资实现收益最大化.使用金枪鱼群优化(TSO)算法寻参的长短期记忆(LSTM)神经网络为分布鲁棒优化投资组合模型提供收益率的均值与协方差矩阵,求解更符合实际情况的分布鲁棒模型得到投资方案.该模型提出的方案在未来前10 d的收益明显高于直接使用历史均值的分布鲁棒模型,亏损天数少于直接使用历史均值的分布鲁棒模型和平均分配资金的方案.同时该文提出的决策系统随着时间的推移,可以通过更新历史数据重新训练LSTM网络,使得模型保持良好的效果.TSO-LSTM神经网络能有效地抓住股票收益率的历史数据特征,实时动态地为投资者提供良好的投资决策.

基于Shapley值与全局和声搜索算法的电网投资组合策略

随着新型电力系统建设的加速推进,电网投资的力度持续攀升,企业须探索更加合理高效的电网投资策略,以实现最优的综合效益。为此,从经济、社会、环保和安全的维度出发,以电网项目投资的综合效益为优化目标,对投资组合策略进行研究。首先,应用Shapley值法对各效益函数的占比进行分摊,以呈现不同效益指标的特性。其次,在考虑投资能力、负荷需求等关键约束的基础上,设计了电网项目投资组合优化模型,并采用全局和声搜索算法进行求解。最后,构建算例对投资组合策略进行验证。算例结果表明,所提方法能够协助决策者在新形势下制定最优的电网投资策略。

双向证券投资与宏观金融风险:效应与机制

金融双向开放是建设金融强国的必由之路。为推动金融业高水平开放,有必要评估双向证券投资的宏观金融风险。基于2000—2020年20个新兴经济体的季度数据,研究双向证券投资对宏观金融风险影响效果及作用机制。实证结果表明,外商证券投资(FPI)短期内提高新兴经济体宏观金融风险,长期则会降低宏观金融风险,对外证券投资(OPI)对本国宏观金融风险无论短期或长期均未产生影响。异质性分析发现,相较于债权资本,股权资本的风险效应更强;与小规模相比,大规模FPI的风险效应更强;从经济体各部门来看,长短期风险效应适用于企业部门与政府部门,FPI能够抑制金融部门违约风险,家庭部门则并不敏感。机制分析发现,FPI短期内通过促进本国信贷规模扩张提高宏观金融风险,长期通过增强本国金融市场流动性降低宏观金融风险。研究结论可为新兴经济体预防和控制金融风险以及为中国高质量建设金融强国提供参考依据。

考虑投资者过程效用影响的投资组合模型

传统的投资组合模型只考虑投资结果,而未考虑投资过程带来的效用影响。事实上组合投资期间投资者持有的股票价格的每一次波动都牵动着投资者的神经,带来或正或负的效用,影响投资者的投资决策。分析投资者过程效用的影响因素,设计出风险投资者的投资过程效用函数。并假设投资者的总效用函数为过程效用函数和结果效用函数的线性组合,构建考虑投资行为过程效用的投资组合模型,对模型的解进行数值模拟分析。研究结果表明:对损失过于敏感的投资者受过程影响越大,则投资风险资产的资金比例越低,对损失不敏感的投资者受过程影响越大,投资风险资产的资金比例越高。因此,对损失越不敏感且受过程效用影响越严重的投资者,越容易推高市场风险。对模型的投资绩效进行了实证检验,结果发现:受投资者过程效用影响大的投资组合模型在股市持续上涨阶段的投资表现较好,而在股市盘整阶段和持续下跌阶段表现较差。表明受过程效用影响大的投资者会在股市持续上涨时积极入市,在股市持续下跌时迅速退市,从而加剧股市震荡。

基于动态选择预测器的深度强化学习投资组合模型

近年来,投资组合管理问题在人工智能领域得到了广泛的研究,但现有的基于深度学习的量化交易方法还存在一些问题。首先,对股票的预测模式单一,通常一个模型只能训练出一个交易专家,交易决策也仅根据模型预测结果作出;其次,模型使用的数据源相对单一,只考虑了股票自身数据,忽略了整个市场风险对股票的影响。针对上述问题,提出了基于动态选择预测器的强化学习模型(DSDRL)。该模型分为3部分,首先提取股票数据的特征并传入多个预测器中,针对不同的投资策略训练多个预测模型,用动态选择器得到当前最优预测结果;其次,利用市场环境评价模块对当前市场风险进行量化,得到合适的投资金额比例;最后,在前两个模块的基础上建立了一种深度强化学习模型模拟真实的交易环境,基于预测的结果和投资金额比例得到实际投资组合策略。文中使用中证500和标普500的日k线数据进行测试验证,结果表明,此模型在夏普率等指标上均优于其他参照模型。