Data Envelopment Analyses
Seyedeh Masoumeh Mirsadeghpour Zoghi; Masoud Sanei; Ghasem Tohidi; Shokoofeh Banihashemi; Navideh Modarresi
Abstract
Purpose: Portfolio optimization is a selection of assets with the lowest risk and highest return. Asset performance evaluation is a useful way to choose assets and construct a profitable portfolio. For this purpose, the non-parametric Data Envelopment Analysis (DEA) method is used, which is a suitable ...
Read More
Purpose: Portfolio optimization is a selection of assets with the lowest risk and highest return. Asset performance evaluation is a useful way to choose assets and construct a profitable portfolio. For this purpose, the non-parametric Data Envelopment Analysis (DEA) method is used, which is a suitable tool for measuring performance. By the fact that stock returns are not normally distributed and usually exhibit skewness, kurtosis and heavy-tails, which definitely affects the assets performance, we have to consider the characteristics of the returns distribution. In the proposed model, we apply the Variance Gamma (VG) process, which covers the skewness and kurtosis of returns. As a result, we construct a portfolio by selecting assets which their performance is more realistic.Methodology: In the introduced model, the only input of the model is Conditional Value at Risk (CVaR), and the mean return and Sharpe index are the model’s outputs. Since the outputs can be negative, the model is inspired by VRM in the output-oriented DEA model, which deals with negative values. As the returns on stock are VG distributed, its parameters are simulated by the method of moments estimation, and then the process factors are simulated by the Monte Carlo technique. Finally, the scenarios of returns are obtained, and the assets performance is evaluated.Findings: The correctness of the model is investigated by evaluating the relative efficiency of 7 companies from different industries in Iran Stock market. The results show that by considering the returns distribution characteristics, the input and outputs values of the model are estimated more realistically and more reliable results can be obtained; thus a profitable portfolio can be constructed.Originality/Value: Evaluation of the assets performance by taking into account the returns distribution characteristics leads to realistic results.
Data mining and related topics
Saman Haratizadeh; Fatemeh Rezaee
Abstract
Purpose: Selection of the best stocks for the portfolio as well as allocating the optimal amount of capital per stock in the portfolio are serious challenges in investing in the stock market. The use of machine learning capacities in the process of optimal capital allocation among portfolio assets has ...
Read More
Purpose: Selection of the best stocks for the portfolio as well as allocating the optimal amount of capital per stock in the portfolio are serious challenges in investing in the stock market. The use of machine learning capacities in the process of optimal capital allocation among portfolio assets has received less attention and usually, the same weight is assigned to portfolio stocks or traditional risk assessment methods are used to divide capital between portfolio stocks. The common disadvantage of these methods is that they all use simple and inflexible mechanisms to estimate the performance of a set. The purpose of this paper is to show for the first time, that machine learning can be used to create a more effective mechanism for estimating performance, which leads to a more efficient allocation of capital to portfolio stocks.Methodology: Our proposed framework, uses two predictive models based on machine learning. In the first step, stocks historical information is used in a return forecasting model, then based on the predicted returns, the appropriate stocks of the portfolio are selected. In the second step, a separate forecasting model predicts portfolio returns by taking into account both the forecasted returns in the first model and the expected risk of the stocks. At the end based on the predicted return of the numerous random portfolios, the appropriate weight for each asset is selected.Findings: Comparing the returns of adjusted portfolios with this model and adjusted portfolios with other portfolio optimization methods shows the superiority of the proposed model.Originality/Value: In this paper, by using machine learning models, the process of selecting the appropriate stock of the portfolio and allocating capital among the candidate stocks is done optimally.
Financial modeling
Ebrahim Mirmohammadi; Mehdi Madanchi Zaj; Hossein Panahian; Hossein Jabbary
Abstract
Purpose: Risk parity is one of the stock portfolio selection models that has received a lot of attention since the US national financial crisis in 2008. The philosophy of this model is to allocate an equal amount of portfolio risk between the assets. In the present study, the portfolio selection model ...
Read More
Purpose: Risk parity is one of the stock portfolio selection models that has received a lot of attention since the US national financial crisis in 2008. The philosophy of this model is to allocate an equal amount of portfolio risk between the assets. In the present study, the portfolio selection model is introduced which is a combination of risk parity portfolio and factor analysis with the Markov regime-switching framework.Methodology: The portfolio selection model is introduced which is a combination of risk parity portfolio and factor analysis with the Marko. Regime-switching framework approach. Markov regime switching helps to make the covariance matrix in the objective function of the risk equality model dependent on the state variable and increase the stability of the portfolio. At the beginning of each investment period, the state variable is determined and the asset covariance matrix is calculated based on it and used in the risk equality modelFindings: The research portfolio consisting of 8 industries from the Tehran Stock Exchange in the period 1390 to 1399 shows that this portfolio has a higher sharp ratio than the mean-variance and equally weighted portfolios in market declines, it is more durable and produces less damage.Originality/Value: The innovation and importance of research is robustness of risk parity portfolio by considering the covariance matrix parameter with factor analysis in Markov regime-switching framework. Thus, it is expected that in different market situations, expectations from the stock portfolio will be more consistent with reality and less losses will be produced in market declines.