Search

In the traditional portfolio models, the return rates of risky assets are usually defined as random variables or fuzzy variables. However, when some events such as financial crises or wars occur that can cause instability in financial markets, the results of these assumptions are not always satisfactory. Therefore, some scholars try to use uncertain variables to express the return rates. In this paper, a two-factor uncertain portfolio problem under optimistic value criteria is studied, where we use the optimistic value instead of expected value to describe the investment return and study the impact of economic circumstance factor and corporation's specificity factor on the return rates. Firstly, a two-factor optimistic value-variance-entropy model with background risk is constructed, in which the total investment return consists of the risky asset return and the background asset return. Then, considering the investors with two kinds of risk preferences, a three-step method is applied to convert the bi-objective optimization model. Moreover, a moment estimation method is used to process the expert-estimated data on the return rates. Finally, a numerical simulation is presented for showing the applicability of our models and solution method. • We use optimistic value to represent the return rather than expected value. • The multiple factors and background risk are considered simultaneously. • Three-step method is used to convert the model into two single-objective models. [ABSTRACT FROM AUTHOR]

With the development of financial market, people invest their savings into different financial products to increase return. However, financial market is an extremely complex system, where investment opportunities and risk often coexist. For investors, it is necessary to take effective measures to avoid risk while obtaining considerable return. In recent decades, actively managing investment in the form of a portfolio is widely accepted by investors. In this paper, we propose a new three-objective Sortino ratio-expected shortfall-turnover rate (SR-ES-TR) portfolio optimization (PO) model. The Sortino ratio is used to measure the risk-adjusted rate of return. The expected shortfall is used to measure the tail risk of a portfolio. Portfolio liquidity risk is characterized by turnover rate. We constructed a portfolio of ten stocks and solved the SR-ES-TR model by the novel MOPSO-SODE algorithm. Compared with other four multi-objective algorithms, the better performance and validity in solving SR-ES-TR model by MOPSO-SODE algorithm have been verified. • Established a three-objective SR-ES-TR portfolio optimization model with liquidity ratio. • Designed a MOPSO-SODE algorithm based on the MOPSO framework. • Verified the effectiveness of the MOPSO-SODE algorithm in solving SR-ES-TR model. [ABSTRACT FROM AUTHOR]

Abstract: In strategy of investment, an important thing for investors is to correctly predict firm’s revenue growth rate (RGR), which is an effective evaluation indicator for them to see how big the potential power of future development is and measure how about the growth of future development for a target firm that may be selected to investment portfolios. However, conventional methods of forecasting RGR have some shortcomings such as statistical methods based on strict assumptions of linearity and/or normality limit applications in real world. Additionally, due to rapid changing of information technology (IT) today, some techniques (i.e. rough sets and data mining tools) have become important research trends to both practitioners and academicians. With these reasons above, a new procedure, using the feature selection method and rough sets classifier, is proposed to extract decision rules and improve accuracy rate for classifying RGR. In empirical study, an actual RGR dataset collected from publicly traded company of stock markets is employed to illustrate the proposed procedure. The experimental results of RGR dataset analyses indicate that the proposed procedure surpasses the listing methods in terms of both higher accuracy and fewer attributes, and the output of proposed procedure is to generate a set of easily understandable decision rules that are readily applied in knowledge-based investment systems by investors. [Copyright &y& Elsevier]

Abstract: Lowering psychological pressure of investors and increasing the futures trading profit are the main purposes of this paper. First of all, this study aims to transfer profit curve (PC) generated by a non-AI-based trading strategy into technical indices, and enable clustering of high-low points of PC to display high–low point signals through some AI-based methods such as Grey Clustering, SOM and K-mean. Next, it attempts to close the transaction with high-point signal, and then open a position at low-point one, thus constructing three groups of profit refiners: GCR (Grey Clustering Refiner), SOMR (SOM Refiner) and KMR (K-Mean Refiner). Finally, the features of these refiners are analyzed to evaluate the test results using some performance indices. SOMR could improve the profit to the greatest possible extent, followed by GCR and KMR; on the other hand, KMR could lower psychological pressure, followed by SOMR and GCR. As a whole, three groups of refiners can really improve the profit and alleviate psychological burden of investors. [Copyright &y& Elsevier]

Abstract: Portfolio selection is a resource allocation problem in a finance market. The investor’s asset optimization requires the distribution of a set of capital (resources) among a set of entities (assets) with the trade-off between risk and return. The ANN with nonlinear capability is proven to solve a large-scale complex problem effectively. It is suitable to solve NP-hard resource allocation problem. However, the traditional ANN model cannot guarantee the summation of produced investment weight always preserves 100% in output layer. This article introduces a resource allocation neural network model to optimize investment weight of portfolio. This model will dynamically adjust the investment weight as a basis of 100% of summing all of asset weights in the portfolio. The experimental results demonstrate the feasibility of optimal investment weights and superiority of ROI of buy-and-hold trading strategy compared with benchmark Taiwan Stock Exchange (TSE). [Copyright &y& Elsevier]

• A cloud theory-based multi-objective portfolio selection model is proposed. • The crisp numerical characteristics of the cloud model theory are defined. • The acceptance and rejection functions with variable risk appetite are constructed. • A compromise programming approach is utilized to aggregate the objectives. • Several schemes as per investors' preferences regarding all objectives are devised. This study proposes a cloud theory-based multi-objective portfolio selection model with variable risk appetite, which incorporates four objectives of mean, variance, skewness, and liquidity constrained by several realistic constraints. Cloud model theory is employed to characterize the return rates and liquidity of assets due to the superiority of simultaneously capturing the ambiguity and randomness of information. The crisp numerical characteristics of the cloud model are defined to obtain the crisp form of the proposed model. To highlight and portray the investors' risk (averse-neutral-seeking) appetites, the generalized acceptance and rejection functions are modeled by using the extreme values of each objective and introducing a variable risk appetite parameter. Thus the corresponding model is transformed with the objective functions of maximizing acceptance and minimizing rejection, which is solved through the compromise programming approach. The extended model provides investors with an opportunity to adjust risk parameters according to current market status. Moreover, the preference ratio vector is introduced when optimizing, which provides investors with overall control over the preferences regarding all objectives, so that investors can derive optimal portfolios well compatible with their expectations through customized weighting schemes. A real-world empirical application is presented to demonstrate the effectiveness of the proposed model [ABSTRACT FROM AUTHOR]