جستجوی مقالات مرتبط با کلیدواژه « شبکه عصبی مصنوعی » در نشریات گروه « اقتصاد »

Considering the current economic conditions of the country, the number of helpless companies and the importance of financial helplessness are increasing day by day. The increase in economic factors affecting financial helplessness has also increased the complexity of investment decisions for these companies. For this purpose, the approach presented in this research, taking into account various financial criteria, provides the possibility of dynamic forecasting of Financial Distress for these decision makers. makes The approach introduced in this research is first by clustering the companies in the proportional cluster of financially helpless and non-helpless with the help of artificial neural network method, self-organizing mapping (SOM) and then by using the data envelopment analysis method based on the worst performance (WPF-DEA). A dynamic forecast of the financial helplessness of the companies admitted to the Tehran Bahadur Stock Exchange was carried out. Using the mentioned method, 105 companies were evaluated and the result of the inefficiency of these companies was predicted during 5 time periods from 2015 to 2019. The dynamic data coverage analysis model based on the worst performance has the ability to evaluate the inefficiency of the examined units, including companies that are members of the Stock Exchange and Securities Organization. Data envelopment analysis has been able to successfully identify the financial helplessness of companies as inefficient decision units.

In recent years the use of artificial intelligence techniques in the financial and investment markets instead of customary quantitative methods has been increasing and gives better performance towards classic methods usually. Artificial Neural Network (ANN), has weaknesses points despite its enormous benefits also. In this study, in order to overcome the weaknesses of the network consists of combining artificial intelligence methods with Evolutionary algorithms, means of artificial neural network combined with genetic algorithm (GA) and Particle Swarm algorithm (PSO) to model and daily predict of nominal exchange rates or the exchange rate dollar by Rial in Iran in the period 21.03.2013 to 22.12.2019 is used. This combined model with neural networks method as one artificial intelligence model according to the criteria of MSE , RMSE, MAE, U.Theil compared. The results of this research show the superiority of synthetic neural network model -Particle Swarm algorithm compare to other models of investigation.

Lack of liquidity management of banks is one of the most important risks for any bank and if less attention is paid to liquidity risk, it may lead to irreparable consequences; Preventing liquidity risk requires a comprehensive measurement method but liquidity risk is complicated issue, and this complexity makes it difficult to provide a proper definition. In addition, defining liquidity risk determinants and formulation of the related objective function to measurement its value is a difficult task. To address these problems, in this study we propose a model that uses artificial neural networks and Bayesian networks. Design and implementation of this model includes several algorithms and experiments to validate the proposed model. In this paper, we have used Lunberg-Marquardt and Genetic optimization algorithms to teach artificial neural networks. We have also implemented a case study in Bank Mellat to demonstrate the feasibility, efficiency, accuracy and flexibility of the research liquidity risk measurement model.

Lack of liquidity management of banks is one of the most important risks for any bank and lack of attention to liquidity risk leads to irreparable consequences. Preventing liquidity risk requires a comprehensive measurement method but liquidity risk is complicated issue, and this complexity makes it difficult to provide a proper definition. In addition, defining liquidity risk determinants and formulation of the related objective function to measurement its value is a difficult task. To address these problems and assess liquidity risk and its key factors, in this study we propose a model that uses artificial neural networks and Bayesian networks. Design and implementation of this model includes several algorithms and experiments to validate the model. In this paper, we have used Levenberg-Marquardt and Genetic optimization algorithms to teach artificial neural networks. We have also implemented a case study in Bank Mellat to demonstrate the feasibility, efficiency, accuracy and flexibility of the research liquidity risk measurement model.

Earning of companies is one of the important factors in economic growth and development and earning manipulation is one of the main challenges of market efficiency that researchers often use accounting data to predict earning manipulation, while non-accounting data also play an important role in predicting earning manipulation.Due to the fact of the conducted research in order to develop the Beneish model has been formed solely because of accounting data, so the effects and consequences of non-accounting variables in all models have been ignored. This study tries to examine the nonlinear relationships of accounting and non-accounting variables and examine the effect of both variables simultaneously. The purpose of this study is to measure the predictive power of Beneish model and the development of the Beneish model (DBM) by non-accounting variables and to compare the accuracy of earning manipulation prediction of the research models using a hybrid Artificial Neural Network trained by Particle Swarm Optimization (PSO) algorithm and Imperialist Competition Algorithm (ICA).Theoretical Framework: The development of the Beneish model (DBM) was done through emphasizing non-accounting variables, including the Information Asymmetry (IS) and Product Market Competition (PMC).(Asgari Alouj et al, 2020). Another study by (Pourali & Kouchaki Tajani, 2021) was conducted to compare the accuracy of companies' profit manipulation predictions using colonial competition algorithm and genetic algorithm. The results showed that colonial competition algorithm with 93% accuracy and 7% error and genetic algorithm with 76% accuracy And 24% error could have predicted the coefficients of the variables of the profit manipulation model. The results also showed that the ability to predict the accuracy of profit manipulation model coefficients by colonial and genetic competition algorithms is more accurate than the prediction of the initial model of Banish (1999) .

This research has been developed the Beneish model) BM) with non-accounting variables including information asymmetry (IS) and competition in the product market (PMC). The data of 184 companies listed on the Tehran Stock Exchange during 2006-2017 has been collected and the prediction accuracy of research models has been compared by two algorithms in training of Artificial Neural Network (ANN): Particle Swarm Optimization (PSO) and Imperialist Competition Algorithm (ICA) in detecting and identification of earning-manipulator companies. In this research, the auditor's report has been used as an alternative solution and the review process has been done such that the audit report of the sample companies has been fully reviewed and studied and if there were the cases as an index of earning manipulation (regardless of the type of report acceptable - adjusted - rejected and no comment), the sample companies would be selected as the earning-manipulator firm and the number 1 would be allocated. Also, if there were no clauses as an index of earning manipulation, for example, the report is adjusted for another reason, it would be selected as a non-earning manipulator and the number zero would be allocated.

After reviewing and auditing the audit reports of the sample companies of 1840 data-year, 900 data-year companies has been classified at the low level of earning manipulator companies and 940 data -year companies has been classified at the high level of earning manipulator companies. In this study, the prediction power of earning manipulation companies has been investigated by hybrid Artificial Neural Network method and Particle Swarm Optimization (PSO) algorithm and also by hybrid Artificial Neural Network method and Imperialist Competition Algorithm (ICA) and a comparison has been made between the accuracy of the research models. The areas under Receiver operating characteristic (ROC) curve of the Beneish model have been estimated up to 0.6001 and 0.5538 using the hybrid neural network trained by Imperialist competition algorithm and particle swarm optimization algorithm, respectively. The area under the ROC curve in the Beneish model has been estimated in the range of 0.5 - 0.6 and indicates the Beneish model test has been rejected in detecting and identifying earning manipulator companies. Therefore, it can be seen that the separation of the two groups of earning manipulator and non-manipulator companies is not significantly different from the separation of the chance model and it can be said that the Beneish model is a completely random model in the Tehran Stock Exchange and cannot be used to identify earning manipulator companies. Also, the best prediction accuracy of the Beneish model has been estimated up to 57.55 and 55.71 percentages using the hybrid neural network method trained by the Imperialist competition algorithm and the particle swarm optimization algorithm, respectively.

Findings indicate that the prediction accuracy of the proposed model has increased from 57.55 to 63.86 percentages and 55.71 to 59.84 percentages by the ANN-ICA and ANN-PSO, respectively. Development of the model, area under curve (AUC) of ROC has been increased and the prediction error has been reduced to 6.31 percentages by the ANN-ICA and to 4.13 percentages by the ANN-PSO, but the test result is still poor. In fact, the accuracy of model prediction by the ANN-PSO has been improved compared to the ANN-ICA.However, it can be seen that relying on these variables by itself could not easily identify earning manipulator and non-manipulator companies. Considering that the proposed model with the variables of Competition in the Product Market and Information Asymmetry has not significantly improved the accuracy of the prediction model, it can be seen that there is a not significant relationship between these variables and earning manipulation variable. In order to judgement whether or not the results of ANN-ICA and ANN-PSO of research models are significantly different, the Wilcoxon test has been performed at a significance level of 5% as the statistical method of non-parametric. The results of Wilcoxon test show that the normal statistic of Wilcoxon test is more than the critical value of 1.64 and the significance level is less than 0.05 in both methods .Also, the average rank has been calculated up to 548.5 before the development of the model and has been calculated up to 5549.7 after the development of the model, so the research hypothesis is confirmed.

Money demand is one of the key variables in the economy which is considered by the policymakers in determining monetary policies. In fact, the impact of monetary policies is transmitted from the money demand channel by the private sector to the real sector of the economy. Therefore, more accurate estimation and forecasting of this variable in terms of environmental factors could be helpful for the monetary policymakers. In the present study, the adjusted function of real money demand with respect to the variables of economic sanctions, economic uncertainties and underground economy by using Markov Switching Model for the period of 1979 to 2018 with two regimes of high money demand (a regime with greater y-intercept) and lower money demand (a regime with less y-intercept) were estimated. The Artificial Neural Network (ANN) method was used in order to forecast the money demand function. Then, in order to ensure the high predictive capability of the ANN method, the forecast was performed by Markov Switching Model. The results demonstrated that Measure of National Income and Output has a positive effect, housing returns (the proxy for interest rates) has a negative effect, exchange rate in both regimes has a negative effect, the volume of the underground economy in both regimes has a positive effect, economic uncertainties in both regimes have a negative effect and economic sanctions in both regimes have a negative effect on real money demand. Furthermore, the results of the forecast indicated that the ANN method has a higher predictive capability in comparison with Markov Switching Model.

One of the new approaches to purchasing and procuring goods and materials in the supply chain is the use of reverse auction. With the rapid and ever-expanding development of information technology and the Internet around the world, the use of Internet platforms for this type of procure has also been taken into account and has created online reverse auction method. In this paper, a new framework for the online reverse auction process is provided that takes both sides of the procurement process (buyer and seller). The proposed auction process is a multi-attribute semi-sealed multi-round online reverse auction. In this process, an online market-maker, with the prediction of the buyer scoring function, facilitates the seller's bidding process. To fit the function, a multi-layer perceptron neural network model is used. In this case, in addition to hiding the seller's scoring function, information is provided to sellers to improve the bid. Also, the methods of scoring by the buyer are defined Additive, Multiplicative and risk aversion, which is based on the theory of perspective. Within this framework, sellers improve their bids in each round using an optimization model. By simulating the auction process, the proposed framework was evaluated in comparison with an open auction, taking into account seller scoring criteria, seller profits, and number of auction rounds

The relationship between social development and resistance economics is a two-way side. It is assumed that social development is the path to a resilient economy in a simplification to better examine this relationship. This study seeks the algorithm, model and method of examining the paths of this effect. Therefore, after reviewing the theoretical literature of the research, the components of the model have been addressed, which by aggregating them, the study model was obtained. The research findings indicate that the obtained model has four input variables such as one output variable, and three hidden layers. There are ten groups in the first hidden layer, six groups in the second hidden layer, and two groups in the third hidden layer. The model is obtained with six inputs. The study method was identified as the artificial neural network method, which has both the ability to simultaneously examine multiple inputs and the ability to predict other possibilities that need to be addressed in other research.