جستجوی مقالات مرتبط با کلیدواژه "particle swarm optimization" در نشریات گروه "مالی"

Today, profit rates and the possibility of managing and manipulating the profits are clear to all, and researchers have always sought solutions to remove the uncertainties facing investors and stakeholders when making their financial decisions. To clarify users' decision path of financial data users, Beneish (1999) has developed a profit-management predicting model that has yielded different results in different societies. Thus, this article aims to optimize and localize Beneish’s model by adding the Tunneling variable to Beneish’s variable and using a modern neural network and particle swarm algorithms. The statistical research population consisted of 196 companies listed at the Tehran Stocks Exchange from 2014 to 2019. The research method was a descriptive-library method in which the variables are interrelated through the causal-correlational method. From an objective point of view, it is an Ex-Post Facto research design. To analyze the data, the regression method and artificial neural and the PSO algorithms were used. The model analysis results suggested that all financial ratios had significant effects on Beneish’s profit management, as the Tunneling phenomenon and the financial leverage had the highest and lowest effects on predicting Beneish’s profit management, respectively.

There have always been two approaches to forecasting in financial markets: traditional and intelligent approaches. In the traditional method, this forecasting is based on statistical models and in the intelligent method is based on artificial intelligence models. Traditional methods mainly use linear patterns to model market behavior, while the main advantage of smart models is the ability to learn and model nonlinear behaviors in the market. It has always been a question of which methods can better model market behavior, and despite the many models that have been proposed for forecasting, there is still an attempt to build a model that can use more effective variables for forecasting. Continues to be able to take into account factors such as time, risk and return. In this research, we have used the neural network to predict the industry index. This is done by ELM neural network using two optimization methods OSELM and PSO. The results show that the prediction accuracy of these two methods is not significantly different from each other, but in terms of execution time, the OSELM neural network algorithm has performed much better and faster.

Choosing the optimal stock portfolio is one of the main goals of capital management. There are several techniques and tools to solve problem the optimal portfolio. In this research, using data of 15 stocks which randomly selected from the Tehran Stock Exchange including; PKOD, ZMYD, BPAS, FOLD, MKBT, GOLG, MSMI, PTAP, SSEP, AZAB, FKAS, NBEH, PFAN, GMRO and GSBE, the First return of these stocks are calculated daily in the period of 31/3/1394 -31/3/1399 for 5 years for 1183 days. Then and their portfolio risk is calculated using the models of absolute deviation risk and conditional value at risk, and these two criteria are compared by the classical solution method. The portfolio optimization output with each of these risks represents a different weight per share. In the following, the deviation - absolute risk model and conditional value at risk model of metaheuristic method using MATLAB (R2019) software are compared. The results show that the PSO model of metaheuristic method compared to the classical method in solving portfolio optimization problem showed more return in PSO-MAD criteria and therefore it is a better method to solve such portfolio optimization problems.

In this research, a model for analyzing and predicting the noisy financial time series of stock prices using singular spectrum analysis and support vector regression along with particle swarm optimization is presented. Thus, the time series of closed prices of 140 shares of companies in different industries per minute per day for the period from 28 May to 11 June for the years 1392 to 1398 was examined separately from the Tehran Stock Exchange. Also, the performance of the proposed model was compared with the performance of four wavelet transform models with neural network, moving average regression process, polynomial regression and naïve model. Mean absolute error, mean absolute error percentage, and mean square root of error were used as the main performance criteria. The results show that the performance of the proposed model for analyzing and predicting noisy financial time series based on mean absolute error, mean absolute error percentage and mean square root of error is better than other models (including: wavelet transform, moving average self-regression, regression Polynomial is the naïve model).

According to capital market research, the negative shock of stock price in any market is a function of environmental factors and specific characteristics of the company and any insight into how to describe and predict the shock can influence the decisions of investors and stakeholders. In this study, based on the data related to 96 financial ratios of 140 companies listed on the Tehran Stock Exchange during a period of 9 years between 2010 and 3012, we have predicted a negative shock of stock price based on the meta-heuristic approach. In this research, in order to extract the optimal financial ratios, genetic algorithms and particle swarm optimization have been used. The proposed model is then tested using these extracted features by a support vector machine with a radial core and an artificial neural network. The results showed that the variables extracted from the particle swarm optimization algorithm, together with the support vector machine learning algorithm, create better results for predicting shocks (temporary and permanent) and their number.

Since the problem of optimizing the stock portfolio in nonlinear conditions with multi-objective functions cannot be effectively solved using traditional and traditional approaches, in this research, a metaheuristic approach is proposed to optimize the stock portfolio using the particle swarm optimization technique. This method has been implemented on a variety of investment portfolios with selection constraint and unconstraint conditions for the investor. By implementing the algorithm and in order to validate it, the results were compared with the genetic optimization algorithm. The computational results indicate that particle swarm optimization algorithm has a good performance, so that the results seem very promising and satisfactory for use in real conditions.

The choice of stock portfolio is a special issue in the field of investment. Given the wide range of options in the stock market, one of the major concerns of investment groups is the optimal allocation of assets. Therefore, most of these collections use portfolio selection models. The conditional value at Risk, which is one of the models of portfolio selection, follows the Quadratic Programming. Given that Quadratic Programming requires extensive computations, the use of metaheuristic algorithms in solving these problems increases the speed and accuracy of computations. The aim of this study is to minimize the Conditional Value at Risk by using two algorithms of Imperialist Competitive Algorithm and Particle Swarm Optimization. Therefore, using 800 days of data from 12 companies listed on the Tehran Stock Exchange in the period of 2/5/92 to 1/28/98, portfolio has been formed, and the weight of each stock in the optimal portfolio and the risk and return of the portfolio has been calculated using MATLAB2018 software. Then, using SPSS software, the average difference between risk and return of the two algorithms was tested. The results showed that the risk and return of the two algorithms were not statistically significant,.

Increasing the competitiveness of countries in the world can be reached only through innovation and the financial aspect is the most important pillar of a national innovation system. Hence, the role of venture capital in developing knowledge-based institutions is vital. However, startup portfolio selection and venture capital firms’ syndication have always been critical challenges in VC industry. Hence, the need for integrated methods, based on sophisticated quantitative techniques, is always being felt. In this research, the simulation of startup portfolio optimization is much more similar to real world and the preferences of startups as decision-makers and the interaction between investees and investors are considered. The results could shed light on which investors regarding their attributes and the startup's attributes should syndicate together and how much is their shares.

Considering the complexity of the problem, the best-known model to simulate the problem is an agent-based modeling. By applying two different computational engines based on ANFIS and ANFIS tuned by PSO and also through the utilization of modified HS, the optimization procedure is preceded.

The proposed solution method is applied to about four various samples and has been executed five times independently. Regarding analysis, the computational engine based on ANFIS tuned by PSO is more efficient and the optimum portfolio is achieved based on it.

Regarding the assumptions of the problem and the agent’s attributes in venture capital, the investors’ portfolios and their syndication has been optimized in order to lessen risk and increase return on investment.

Undrestanding the earning management for the users of accounting information due to performance evaluation, profitability forecast and detrmining the value of the company is very important.The purpose of this research is to estimate the a model for earning management using neural network model and then the use of Genetic Algorithm, and Particle Swarm Optimization to find a better combination of input data, so that it can optimize the initial model. For this purpose, 28 effective variables were used in the from of four groups (Financial, managerial, corporative and audit) during the years 2010 to 2016 in the companies admitted to the Tehran stock Exchange. The results showed that application of this algorithm has increased the efficiency of the model.Also, the evaluation of the performance of neural network patterns suggests the absolute superiority of this pattern compared to the time linear method (LR).Combined method (A-PSO) and (A-GA)by identifying four optimal variables respectively precision forecast, shareholding of major shareholders, company size and the ratio of the quality of earning management are carefully predicted respectively (%95/59) and (%94/75). In addition to the above mentioned intelligent methods, by improving correlation coefficient and error squares mean criterion compared to linear methods (LR) and neural network method (ANN) in predicting group results, management and corporate features are more efficient.

Portfolio selection is one of the vital financial challenges. This study seeks to apply the multi-objective water cycle algorithm (MOWCA) to find efficient frontiers associated with portfolio. This problem is non-linear multi-objective problem including maximiaing return and minimizing risk of portfolio. The inspired concept of WCA is based on the simulation of water cycle process in the nature. At the first time, it was applied by Moradi et al. (2017) for optimizating portfolio. Computational results are obtained for analyses of daily data for the period 2013 to 2015 including TSE 30. The performance of the MOWCA for solving portfolio optimization problems has been evaluated in comparison with other multi-objective optimizers including the MOGA and MOPSO. Four well-known performance metrics are used to compare the reported optimizers: GD, MS, S and ∆. Statistical optimization results indicate that the applied MOWCA is an efficient and practical optimizer compared with the other methods for handling portfolio optimization problems.

One of the most applicable optimization approaches used in different sciences is Meta-heuristic Algorithms. This study, by new Meta-heuristic Algorithms, Symbiotic Organisms Search (SOS), introduces the model for selection of optimum portfolio and then the result is compared with the result of older algorithm, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). Therefore, the ten-month information of operation of 50 top companies in the Stock Exchange is extracted and estimated an optimized portfolio with the objectives of maximum efficiency and minimum risk by Symbiotic Organisms Search (SOS), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) is estimated. The results of the algorithm showed that despite the ability of these algorithms to portfolio optimization, SOS algorithm has a higher ability to optimization.

The prediction of future fluctuations in stock index can provide information about the future trend in the capital market. In order to increase the accuracy of the prediction of stock exchange index, this study used a combination of statistical methods and artificial intelligence. In this study, a hybrid stock index prediction model by utilizing principal component analysis (PCA), support vector regression (SVR) and particle swarm optimization (PSO) is proposed. In the proposed model, first, the PCA is used to deal with the nonlinearity property of the stock index data. The proposed model utilizes PCA to extract features from the observed stock index data. The features which can be used to represent underlying/hidden information of the data are then served as the inputs of SVR to build the stock index prediction model. Finally, PSO is applied to optimize the parameters of the SVR prediction model since the parameters of SVR must be carefully selected in establishing an effective and efficient SVR model. The findings show that preprocessing the data can decrease the prediction error of the model significantly.

The trend of the stock price index, has taken as one of the investment criteria consistently. Because of the two components of nonlinear and time series price index volatility, in this study, a new hybrid model presented that can predict move and change of these two components of the trend of the index with the highest accuracy. In this model, at the first by using wavelet transform the index time series splits into six separate time series index which represent the characteristics of nonlinear and volatility of index. Then the derived time series with nonlinear behavior by combining the support vector machine and particle swarm optimization (SVM-PSO) and time series behavior based on index volatility by using GJR models predicted and then by accumulating results of two nonlinear and volatility of price index prediction component, price index time series estimates. The results show that the proposed hybrid model, in comparison to other forecasting methods, has fewer errors and higher accuracy.