نشریه مهندسی مالی و مدیریت اوراق بهادار
پیاپی 50 (بهار 1401)

The purpose of this study is to select the optimal stock portfolio using data envelopment analysis and to carry out the project of stock exchange information about the top 50 active companies in the summer of 1398 and trace the analysis of the same data in the spring of 1398. To calculate the relative efficiency and progress of companies, a developed data envelopment analysis (SORM) model has been used, where inputs can be changed only at a limited and specified distance, and with the same assumption, the output can be limited to a limited distance. The negative data can be analyzed and the final model facilitates the efficiency and optimization of stock portfolio selection according to the information extracted from the community under discussion. The results of this analysis show that 13 companies achieved a performance equal to 1, which indicates the highest level of efficiency, and Bank Saderat, including 1.32 Fanavaran Petrochemical Company, with the figure of 1.15, has been classified as having the highest progress and growth rate, respectively, on the first and second floors of productivity.Keywords: negative data, data envelopment analysis, ranking indicators, super performance, progress and regression.

This study compares the credit risk of banks from the perspective of stakeholders through two models based on accounting information and a model based on market information. The purpose is to evaluate the performance of models that estimate the bank's credit risk either from accounting data or share price information. In Merton model, the value of equity is determined and by estimating the daily value of assets according to the model and comparing it with the value of debts, the bank's credit risk is determined. In the Logit model, changes in the NPL of the bank is compared with this ratio in the industry and credit risk is considered as a binary variable. The Z-score model uses changes in the ratio of return on assets and the ratio of equity to total assets and standard deviation of return on assets. Independent research variables are five groups leverage ratios, management efficiency, profitability quality, financial health, and liquidity. In this study, a sample of banks during the period from 2007 to 2017 has been selected and using the Rock Statistics test, all models are above the middle and are efficient. Their efficiency, respectively is 99.48%- 98.38% and 92.68%.

In this study the usefulness of expected credit loss of loan facility compared with loss impairment for predicting banks, future profitability was tested. The model of Altamuro and Beatty (2010) and Kanagaretnam et al. (2014) was applied for predicting banks, future profitability and for calculating fair value of loans was applied the model of Tschirhart et al. (2007) and expected credit loss is calculated by fair value of loans. The hypotheses of the study were tested through the panel data gathered from 18 listed banks in Tehran Stock Exchange.The findings of the first hypothesis of the research indicated that with 95% assurance loss impairment has a significant and negative relation with one year-future profitability and expected credit loss has no effect. The findings of the second hypothesis of the research indicated that with 95% assurance both of expected credit loss and loss impairment have a significant and negative relation with two year-future profitability. Also the size of assets has a significant and positive relation with one and two year-future profitability.

Finding the best way to optimize the portfolio is one of the concerns of activists in the investment management industry. In recent years, the introduction of economic and mathematical models in the prediction of Gold indice has helped many investors to optimize portfolios. Therefore, in this study, we introduce models of GARCH family composition and convoultional neural network to predict the daily yield of Gold index will be paid during the period of 1390-1398. In this study, the Gold index is examined using GARCH and EGARCH short-term memory models. Of the two variables, the price of crude oil and the dollar index as factors that their shocks and fluctuations have a major impact on Gold indices are used as control variables. In addition to using convolutional model, considering the better performance of combined models (compared to individual models ) In anticipation In this study, all models of the GARCH family (both short and long run) with the convoultional neural network were combined and using the combined models, the efficiency of the main stock index and the five selected indicators for the next 10 days were predicted step by step and its accuracy Based on the evaluation criteria.

Data envelopment analysis is a non-parametric method for measuring the performance score of a set of units under evaluation. Recently, the application of data envelopment analysis models in networked or multi-stage structures has been considered by researchers. This paper seeks to reinforce the first steps taken to develop DEA network models based on asynchronous technology. To this end, it provides a way to consider undesirable outputs in an asynchronous technology. The models presented in this paper, while calculating the overall performance score in a network system, are able to calculate the performance of each step separately in the presence of undesirable factors without any additional calculation and provide it to the system administrators. Also, to show the accuracy of the proposed model compared to the basic CCR model, we conclude the computational accuracy of the model due to the identification of a number of less efficient units than the CCR model. According to the results, despite the fact that some units are considered as efficient, but due to inefficiency in some stages are considered inefficient and only the National Industrial Holding is considered as the only efficient unit due to the fact that it is efficient in both stages.

Macroeconomic policies are an important tool for governments to achieve financial commitments andtheir social and economic goals. Macroeconomic policies have different types and their implementationcan effects different markets in various ways which can cause change and turbulence in them. With thisapproach, in the present study by using the Bayesian Causal Map (BCM) and seemingly unrelatedregression equations (SURE) model, a model is designed to explain the effect of macroeconomic policieson money and capital markets. It should be noted that the time period of the present study was 1989 to2019. The results of the present study showed that money and capital markets are affected by variablesand policies applied in different markets in both direct and indirect ways. If the amount of savings in thesociety changes as a result of government policies or other economic and non-economic components,the facilities granted by the banking system will change as well. This directly affects the money market.Given that changes in the money market affect the capital market, the capital market is also affected bychanges made in the money market. At the same time, changes in the money market also affect othermacroeconomic variables such as................

We introduced estimation methods include the market value proxy , volatility restriction , KVM , and the transformed-data maximum likelihood with strengths and weaknesses in order to estimate distance to default . If the correct estimation method is not used, there will be distortion in the results . Considering the different balance sheet structure , the transformed- data is introduced by considering the coefficient of other debts as an optimal method in order to estimate distance to default in banks. Then, we used Merton's adjusted model and the transformed- data method during 2012 to 2019 to calculate market value of assets, asset volatility, distance to default, and probability of default in some private banks. The results show that the highest market value of assets is related to Bank Mellat and the lowest is Post Bank . The results achieved by comparing are different regarding volatility of assets, distance to default, and the probability of default. Additionally, the average market value of banks' assets is increasing and the average volatility of assets and the average distance to default is decreasing . In other words, Banks have become closer to default . The Dickey-Fuller test confirms the Stationary of the research model.

If the asset market is information-efficient and people behave rational, asset prices reflect available information about expected events. On the other hand, choosing the right policy is important in economic stability.Since traditional models have failed to identify correct and appropriate policies, using time varying methods, can select the policy according to the current situation.Based on Bayesian averaging method, the variable total government expenditures was determined as the most fragile variable affecting the asset prices. so, in the TVP-FAVAR model, the effect of this variable on the price of each asset in different time periods in MATLAB has been investigated.According to the results, expansionary fiscal policy, in the long run, has had a positive effect on the price of each asset. This effect on the exchange rate variable has intensified in recent years. It should be noted that based on the results in recent years, fiscal policy has had a negative impact on housing prices and the stock market and has reduced the price of these assets. Also, the fiscal policy shock in short run, on the stock market, in medium term, on the housing index and in long run, has the highest impact on the exchange rate.

After the broadcast world and the epidemic of pandemic covid-19 was a severe economic crisis, For this reason, the need for more prediction became apparent. One of these methods is time series prediction. In this study, first, the effect of covid-19 disease on price of Ethereum and Bitcoin, and the results show that this disease had a negative effect on world prices of Ethereum and Bitcoin. In the next step, using univariate time series methods and with the help of ARIMA models, a model for predicting which is the best model AR (1) and MA(1) and time differentiation was designed, the one-year and two-year forecasts were done with the designed model. According to the reports of the World Health Organization, there is probably corona pandamic for up to one year, and For the next two years, Corona has emerged from a pandemic is called the post-corona period. The results show that After a short decline and reacting to resistance and support, they will have an annual upward trend.

The purpose of this study is to design a credit portfolio optimization model in the banking industry using a meta-innovative algorithm. Risk is one of the basic concepts in financial markets that has a certain complexity. Due to the lack of a clear picture of risk realization, financial markets need risk control and management approaches. The present study is a descriptive survey in terms of data collection and applied in terms of purpose. The statistical population of this research includes all facility files of the last 10 years as well as the financial statements of Ansar Bank branches affiliated to Sepah Bank, which were selected by census method. The risk criteria used in the models are: fuzzy risk value, absolute value of fuzzy downward deviations and half entropy. Research models were implemented using multi-objective particle swarm optimization algorithm. The software used in conducting research is MATLAB software. The results show that the performance of the fuzzy risk-averaged model is better than the other two models in evaluating optimal portfolios. Therefore, the use of the above model in credit basket optimization is recommended.

This is the first study of the newest fields of financial science، financial astrology. Financial astrology states that the position and movements of celestial bodies can affect the financial markets through changes in mood. For this reason، the hypothesis of the effect of lunar cycles on return of the Tehran Stock Exchange has been considered. In this research، the cycles of full and new moon، north and south node، perigees & apogees، lunar declination have been studied. The statistical population of Tehran Stock Exchange and the sample of the overall index for a period of 10 years (90 – 99) have been selected. In this study، nonparametric statistics، Mann-Whitney test were used to test hypotheses and T test was used as a control test. The results show that in Tehran Stock Exchange similar to some researches have been done and contrary to the results of other researches lunar cycles have no significant effect on daily returns. Therefore، the return in different cycles of the moon is not significantly different.

The main purpose of this study is to develop an algorithm trading in turbulent markets. we define turbulent days as days when the absolute values of market returns are greater than 2%. For this purpose, a sample of 276 companies listed on the Tehran Stock Exchange during 2019 has been studied using multivariate regression and logistics. The results showed that in the bullish days of the market, stocks that demand more algorithmic trades have lower abnormal stock returns and have lower price fluctuations. The results for the downtrends showed that the stocks that are traded mostly by algorithmic trading show more downside fluctuations in the downtrends. The results also showed that accounting news and information influence the decisions of algorithmic traders in turbulent days and lead to fewer stock price fluctuations. The intensity of algorithmic transactions about price fluctuations in companies that publish price-sensitive news and information is higher than other companies. In general, the results showed that, compared to non-algorithmic trading, algorithmic trading does not cause price fluctuations between stocks in turbulent markets.

The volume and speed of transactions in financial markets has increased significantly and has undergone extensive changes nowadays. Facing with increasing, decreasing or fluctuating trends in the stock market, determining the right trading strategy is very important. Therefore, complex meta-heuristic models are used for choosing a suitable strategy. In this research, an attempt is made to develop a new method of selecting and optimizing the stock portfolio based on the ensemble learning algorithm and genetics in order to select the best trading strategy to achieve greater returns and less risk. A combination of a six-class support vector machine (SVM) algorithm is used to predict returns and receive a buying signal; besides, a dynamic genetic algorithm is used to optimize trading rules. In this study, collective learning methods including Bagging, one of the algorithms based on Ensemble Learning, have been used to improve the accuracy of classification of returns. Data related to each share and fundamental variables in a daily time interval between years 1390 to 1399 is used as training and test data. The obtained results, comparing to traditional methods, are promising.