فهرست مطالب سعید فلاح پور

This study aimed to evaluate the performance of the gradient boosting decision tree model, the parameters of which were optimized with the improved Gray Wolf Algorithm (GWO) by adding financial network-related variables via the selected models of predicting financial distress. The proposed model of this study was implemented on the data of 123 manufacturing companies admitted to the Tehran Stock Exchange and Iran Fara Bourse Co. (IFB) from 2014 to 2021. Initially, the financial network was formed and then, the financial distress of companies was predicted by integrating the network-based variables with financial ratios and using a gradient boosting decision tree model. The model of the gradient boosting decision tree had better performance in terms of precision and Type I error by adding Financial Network Indicators (FNI) compared to the two models of K-Nearest Neighbor (KNN) and Logistic Regression (LR). Companies with betweenness centrality and high degree centrality were found to be less prone to financial distress and vice versa. This is the first study to predict financial distress by using financial network-related variables integrated with financial ratio variables through the novel gradient boosting decision tree method, the parameters of which were optimized with the improved GWO.

The purpose of this article is to investigate the impact of financial distress risk on the fall in the stock prices of companies listed on the Tehran Stock Exchange. In this research, statistical data of 195 companies admitted to the Tehran Stock Exchange during the years 2015-2019 have been used, and multiple regression using the panel data method has been used to analyze the data. To measure the variable of financial distress risk, Merton's distance to default index and to measure the fall of stock prices, four methods of risk period of stock price fall, negative skewness of stock returns, maximum sigma and low-to-high volatility have been used, as well as asset return ratio variables. leverage ratio, ratio of market value to book value and company size have been used as control variables. The results of the research show that there is a positive and significant relationship between financial distress risk and falling stock prices.

The purpose of this research is to model Value-at-Risk (VaR) of portfolio with EVT-Pair-Copulas approach. In the financial literature, a significant amount of empirical studies have been done on the characteristics of financial assets returns and researchers have found a set of stylized facts about this subject. In this regard leptokurtic, left-skewed, weak autocorrelation, volatility clustering, and heteroscedasticity can be mentioned. Any estimation of risk without considering these characteristics or using unrealistic assumptions about financial assets returns increases the probability of failure in the risk management process. For this purpose, at first, the marginal distributions of returns are obtained using extreme value theory (EVT). Concerning characteristics of financial assets returns and also the primary filter to apply EVT, we use heteroscedasticity models for the marginal distributions of assets. Then the structure of the dependence between different stocks is estimated by using C-Vine, D-Vine, and R-Vine pair copula models. Afterward, the VaR of portfolio is estimated using the Monte Carlo simulation method. The final results show that the model with GARCH marginal distribution and R-Vine pair copula has been able to achieve the best performance among rival models at 95% confidence level.

Stock market manipulation has gained significant attention in recent years. The fact that markets can be manipulated has great implications for designing trading rules and market efficiency. Market manipulation has been developing since the beginning. Thoughtful and accurate manipulation techniques adopted by manipulators may not easily be detected. This research examines stock price manipulation in Tehran Stock Exchange and addresses the identification and detection of stock price manipulation by mathematical algorithm (spoof trading). This study examines transaction-based manipulation in which manipulators place bid and ask orders to control the stock prices. More specifically, this paper studies manipulated stocks by looking at market microstructure (intraday transactions) and aims to introduce an algorithm for detecting suspicious trades so that regulators can detect them beforehand. The ultimate goal of this paper is to help the “Securities and Exchange Organization” (SEO) of Iran to reform market regulations in order to prevent the occurrence of suspicious trades in the market.
This research relies on price data placed by investors in the market. Transaction data consists of two levels; the first level includes executed bid-ask orders available to the public, such as open, close, high, and low prices as well as trading volumes in a specific period. The second level includes the first layer plus all buying and selling orders whether they are executed or not. The latter can only be observed by the regulator and is not available to the public. This paper focuses on the second level in which characteristics and patterns of manipulated stocks are examined by utilizing the intraday transactions of 50 manipulated companies from 2013 to 2016. Panel data analysis and F-limer, Hausman Test, Heteroskedasticity Test, Cointegration Test, Variance Inflation Factors Test, as well as econometric tests relating to price manipulation including stationary, autocorrelation, kurtosis, skewness, run and duration dependence test, were applied to the considered data. Finally, an artificial neural network was used to test the effectiveness of the designed algorithm. The obtained results were illustrated in a confusion matrix.
The results of the mentioned econometric tests were consistent with the results of the designed algorithm. The study’s hypotheses were accepted.
The results of the designed algorithm indicated that the efficiency of the utilized algorithm for detecting suspicious trades is equal to 90.4%, which is an excellent level of performance for accepting an algorithm. Additionally, this research shows that the price and volume of buy and sell orders in the first two lines of the ticker screen are effective in detecting stock price manipulation.

In recent years, deep learning neural networks have been recognized as powerful tools for solving complex problems. Deep learning is a subfield of artificial intelligence in which complex problems with numerous parameters and inputs are modeled based on a set of algorithms. In this research, a new framework of deep learning is presented. Using wavelet transform, stacked auto-encoders, and the Long Short-Term Memory or LSTM, we predict the market direction in the future contracts of gold coins of Iran's Commodity Exchange market. The input data is first denoised using the wavelet transformer in the proposed method. Then, using the stacked auto-encoder, the indicators influencing the market direction are identified. Ultimately, these indicators are given as input to the LSTM architecture to predict the market direction. Proposing several new technical indicators to increase the accuracy of the proposed model, adjusting the parameters of the utilized algorithms, including LSTM, for this problem, and suggesting a trading strategy to achieve appropriate profitability are among the contributions of the present study. Investigations reveal that the proposed method outperforms other approaches and achieves higher accuracy and efficiency.

Transparency of financial information has always been one of the most important concerns of investors and depositors of the banking system. Therefore, the purpose of this study is to investigate the significant relationship between value at risk using book data and market data as a measure of information transparency. For this purpose, at first, the value at risk was calculated using the EGARCH model and then, to examine the significance of the relationship and ranking of banks in terms of information transparency, Pearson correlation coefficient between value at risk (VaR)  calculated from market data and book data has been used. The results showed that in the simultaneous data dimension, there is a weak relationship between book and market VaR  and only the correlation coefficient between book and market VaR of Pasargad and Sina banks are statistically significant at 95% confidence level. If we consider the issue of the speed of book value information spreading in the market with a time lag, the values of the correlation coefficient of book and market VaRs for Parsian, Pasargad and Eghtesad-e-novin banks are significant at 99% confidence level and this coefficient is significant for Sina and Saman banks at 95% confidence level.

Liquidity creation is one of the functions of banks based on the theory of financial intermediation. The purpose of this article is to examine the effects of oil price shocks and economic sanctions on the liquidity creation of Iranian banks, given the country's specific circumstances.

This study was conducted in a nonlinear framework using PSTR models.

Based on the achieved results of this study, the effects of oil price shocks and economic sanctions can be explained using the smooth transition threshold models. Negative oil price shocks have negative effects on the on-balance sheet liquidity creation as well as on the total liquidity creation of large banks but they have a positive effect on smaller banks. The effects of positive oil price shocks are only significant on the on-balance sheet liquidity creation of the larger banks. By examining the average oil price shocks, the results show that oil price shocks harm the liquidity creation of large banks but do not have a significant effect on smaller banks. Economic sanctions have a positive effect on the liquidity creation of large banks and do not have a significant effect on smaller banks.

Overall, the results proved that the effect of negative oil price shocks on banks' liquidity creation is more than the effect of positive oil price shocks and economic sanctions. In addition, mechanisms need to be established to offset its negative effects on banks.

The financial crisis of 2007-2009 led to the redoubled attention of international institutions to the issue of banking regulation. In this regard, the Basel Committee to exercise effective banking supervision reviewed and introduced new standards and requirements in the field of banking regulations, such as capital adequacy requirements, providing liquidity requirements, and leverage ratio. On the whole, studies show that capital ratios have significant and negative impacts on large European bank-retail-and-other-lending-growth in a context of deleveraging and “credit crunch” in Europe over the post-2008 financial crisis period. Additionally, liquidity indicators have positive but perverse effects on bank-lending growth, which supports the need to consider heterogeneous banks’ characteristics and behaviors when implementing new regulatory policies. In this article, by using the data of the Iranian banks during 2006-2018, the simultaneous effect of the new liquidity and capital regulations, inspired by the requirements of Basel Committee and based on the new instructions of the Central Bank, has been studied. In other words, the issue addressed in this paper is what conditions the simultaneous implementation of capital and liquidity requirements by banks will put them in. According to the results, liquidity requirements and capital requirements are complementary. Based on the results, the relationship between liquidity risk (Inverse of Net Stable Funding Ratio) and capital adequacy is positive. Therefore, with the increase of liquidity risk in banks, it will not be possible to establish capital requirements following the provisions of Basel III.

Passive management is an investing strategy that tracks a market value-weighted index or portfolio. It seeks to minimize the cost of investment fees and to avoid undesirable repercussions of the unpredictability of future trends. Active portfolio management tries to beat the market while passive portfolio management pursues a similar risk-return pattern to that of the market index. Index tracking is a passive investment strategy in the stock market that aims to make a portfolio using constituents of an index. It seeks to mimic its behavior without purchasing all of its constituents. This study aimed to track Tehran Exchange Dividend & Price Index (TEDPIX).

In this study, portfolios were tracked and their performances were examined by applying a two-tail mixed conditional value-at-risk model (main model). Optimizing TMCVaR is a linear program that minimizes the upper deviation and the downside deviation from the benchmark index. The investigated sample included the weekly data gathered from 2011/3/21 to 2018/20/3. The data was divided into 26-time frames including 52 in-sample data and 12 out-of-sample data.

Statistical tests confirmed the portfolios resulting from the main model were successful in tracking the index. As a result, the investigated model was recognized as capable of tracking the index. However, due to the tracking error and information ratio, the two models were not statistically different. In the present study, the two models showed the same performance in tracking the index.

In this study, a linear mathematical programming model was proposed to form index tracking portfolios. The results showed that although the main model was successful in index-tracking it did not outperform the mean absolute deviation model in terms of reduction in tracking error and increasing information ratio.

Banks are one of the most important economic pillars of countries that play a significant role in their growth and development. In Iran, due to the expansion of the financial and monetary system, banks have practically taken on the task of collecting and allocating economic resources. One of the important tasks of banks is the optimal management of assets and liabilities with the aim of maximizing returns while minimizing risk. The results of research in this regard show that the optimal allocation of resources leads to increased income and reduced bank risk, will be. In this study, we intend to optimize the real structure by optimizing the structure of assets and liabilities of commercial banks including Mellat, Saderat, Tejarat, Parsian, Pasargad, Eghtesad Novin, Sina, Karafarin, Dey and Middle East using the Mean-Variance model. Letchr('39')s compare the real and optimal structure of banks and then separate the banks into two categories of privatized state-owned banks and fully private banks, examine the effect of management on how to manage the resources and expenses of banks.The research findings show that the combination of bankschr('39') resources and expenditures on some assets and liabilities, including credit facilities granted to customers and banks, as well as current and investment deposits, is significantly different. It is calculated with the optimal combination. The research results also show that the combination of assets, liabilities and equity of private banks is more similar to the optimal composition than privatized state-owned banks, and these banks have performed better in managing their resources and expenditures.

Bank deposits are a very important resource for banks, which, if accompanied by weak investments or fuel facilities, will cause many problems for financial institutions. One way to combat the burning of deposits is to insure them. The present study seeks to provide a model that can measure the risk of the banking industry in proportion to the price of premiums. And it uses risk-based modeling. This modeling uses multivariate GARCH models, which can lead to more accurate pricing of deposit premiums. To determine the factors affecting premiums and determine their relationship, the information of active banks of Tehran Stock Exchange between 1393 and 1397 has been used. Using Blacksholes, Merton Blacksholes, Merton Blacksholes models with systematic risk and Merton Blacksholes models using multivariate GARCH modeling, premium pricing has been done. According to the results obtained from the estimation of regression equations, it was found that the premium received by the Deposit Guarantee Fund was not due to the systemic risk of the banking network and it seems better that the value of the deposit premium is considered considering the risk. Be banking. In this regard, and according to the estimated models, the systemic risk of the banking network better considers the calculated value of the premium by considering the multivariate Garchi model.

In network theory, centrality is a measure to estimate importance and influence of a special node to the whole network structure. The aim of this research is to investigate the characteristics of stock centrality and its reliability in risk estimation and portfolio selection.

First in this paper, we analyzed the relationship between stock’s centrality & benchmark risk estimation measures like beta & standard deviation. Then, we analyzed the relationship between stock’s centrality & Markowitz framework’s weights; and finally, we introduced centrality-based portfolio selection strategy and compared it with other benchmarks, by different portfolio performance measures.

Our observations indicate that in Tehran stock exchange, centrality can have an effective role in stocks risk estimation and there is a meaningful relation between centrality and other measures. We also observed that out that low central stocks can raise the benefits of portfolio diversification, and centrality-based portfolio selection method can have a better performance than other benchmark portfolio selection methods and results in a better risk adjusted return.

Stock centrality, as a measure to estimate importance and influence of member of a network, is capable of describing stock risk characteristics like other accepted measures. We can take advantage of this capability for portfolio selection.

Since the national wealth of oil-rich countries including Iran is connected to petroleum resources, these countries attempt to make their fiscal regimes and licensing system more attractive to international oil companies and investors. On the oil company side risks and uncertainties in oil and gas exploration and production are important challenges when deciding between different projects. This paper identifies the uncertainties and risks present in all stages of an oil and gas development project. Each of the identified risks is quantified using sensitivity analysis. Comparing contractual parameters of Iranian Petroleum Contracts with those of Iran’s buy back contract and other selected oil contract models in the Middle East including Qatar’s production sharing agreement and Iraq’s technical service contract, the paper proposes some changes to the contractual parameters of the Iranian Petroleum Contract. We notice that the amended contract reduces risks both for investing company and IranAfter applying the mentioned amendments, the standard deviation measured for the financial indicators of both the government and the investor was reduced confirming the reducing of contractual risks and improving the contract performance for both parties. In addition, all persons involved in preparation and implementation of Iranian petroleum contract whether as the first or the second party agree with the proposed amendments.

Every investor wants to select the optimal combination of return and risk in order to maximize their utility. In this study, an attempt was made to explain the optimal model for estimating returns and risk in cases where there is a financial crisis and the distribution of return on assets does not follow the normal distribution.For this purpose, we use CAPM with independent and identically asymmetric power distribution (CAPM-IIAPD) and CAPM with independent identically saymmetric exponential power distribution with two tail parameters (CAPM-IAEPD) instead of traditional CAPM. When the assumption of normality is violated, higher moments are used to optimize the model. In the next step, using Polynomial Goal Programming, we calculate optimal portfolios with third and fourth moments.The time horizon of the research from 2011 to 2018 and the statistical population has been all the companies of Tehran Stock Exchange, among which 30 companies have been selected.The results show that CAPM-IIAPD Model is the best model among three models and the adjusted return on risk in optimized models with thirs and fourth moemnts in generalized CAPM models is significantly different from the traditional model and has a better performance.

The interbank market and the activity of banks in financial markets have led to the interconnectedness of banking system. In the normal situation, the interconnectedness will make the system more stable, but in a turbulent condition, the crisis will quickly spread to the entire banking network. In order to effective policy making in financial stability, continuous measurement and monitoring of the level of contagion in the banking network and studying the mechanism of its impact on macroeconomics is required. This paper evaluates the risk of contagion by using Dynamic causality statistics (DCI), and has identified the banks that have a systemic importance in terms of contagion or so-called too-connected-to-fail (TCTF). The relationship between GDP changes and the value added of the financial sector with changes in the DCI index of Iran's banking sector has been evaluated using Granger causality, which indicates a negative relationship up to 12-month time horizon. In order to take a timely measure for decreasing the adverse effects of systemic risks, Policy-makers should monitor DCI index continuously.

Systemic risk is the cause of many financial crises and has adverse effects on economic performance at the macro level. For effective policy-making of systemic risk management, it is necessary to measure and monitor systemic risk and to study the mechanism of its effect on macro-economy. This paper aims at investigating the relationship between banking sector systemic risk and the performance of macroeconomic indexes including Gross Domestic Production (GDP), GDP without oil, the components of GDP and the value added of the sectors.

One of the best systemic risk measures is SRISK index which is used in this article, and the relationship between the changes of macroeconomic indexes and the changes of SRISK is evaluated using autoregressive distributed lags model.

There is a significant negative relationship between the banking sector systemic risk of Iran and GDP (with and without oil) for horizon of 12 months. Value added of construction, financial sector and industry sector is influenced more than other sectors from the changes of systemic risk of banking system. Furthermore, all of the components of GDP are influenced by the changes of systemic risk but this influence is stronger and more durable for the fixed investment component.

In addition to the increase of the probability of financial crisis, the increasing of systemic risk has long-term adverse effects on macroeconomic performance and investments. In order to take a timely measure for decreasing the adverse effects of systemic risks, Policy-makers should monitor SRISK index continuously.

Liquidity Creation is one of the roles that banks play in the theory of financial intermediation, and its components are theoretically related to the economy. In this study, using the methodology of Berger and Bouwman (2009) to compute banks' liquidity creation, we examine the impact of economic sanctions, as well as oil price shocks on the liquidity creation of Iranian banks. Using annual unbalanced panel data and systematic GMM method, the results show the negative and significant effects of oil price shocks on banks' liquidity creation. It has also been shown that oil price shocks have a direct negative effect on liquidity creation within the balance sheet as well as the total liquidity creation. Economic sanctions also hurt liquidity creation and exacerbate the negative effects of oil price shocks. The results of this study provide good policy applications for monetary policymakers.

After the financial crisis in 2008, market practitioners and financial researchers began to attach more importance to risk measurement and modeling. Expected shortfall is recognized risk measures in financial literature.

By the estimation of expected shortfall as a coherent risk measure, and by use of conditional extreme value theory and combining new volatility measures, this research attempts to introduce a new model for risk measurement. Intraday data has been used in this research in order to estimate mentioned risk measures.

The results show that in comparison with alternative models, such as GARCH conditional peak over threshold models, multifractal conditional peak over threshold models, which utilize intraday data, perform better in risk estimation. In addition, the use of extreme value theory brings about more favorable results in risk estimation. In this research, we use a new back-testing models in order to back-test expected shortfall.

The use of the normal distribution function for the disruption components to estimate the expected drop has not been successful, and has led to an estimate of the low risk category. The use of Student's t-distribution in estimating risk measures has been acceptable, although in some cases it has led to an estimate of high risk. Considering extreme value theory of value in the above models has in most cases led to improved model performance. This means that it has moderately adjusted the estimates of the upper hand and the estimates of the.

Financial Stress Index as a measure of a systemic risk that quantify stress throughout the entire financial system and describes the contribution of each section of the financial market to the overall stress of the system. In this paper, a composite index for measuring the stress of the Iran’s financial system proposed using a portfolio approach. This indicator is a combination of stress variables in different parts of the Iran’s financial system (stock market, debt market, banking sector, money market and exchange rate market). To aggregate these variables, EWMA, dynamic conditional correlation (DCC-GARCH) and BEKK-GARCH used to examine the cross-correlations structure between the subindices during the period of March 2010 to March 2018. In the end, to determine which of the stress indicators designed for the financial system of Iran is more desirable, the results of the prediction of the VAR model used to explain the changes in GDP. The results of the comparison of the prediction criteria showed that differences in the performance of these indices are not significant, although the stress index produced by BEKK-GARCH method performed better and in comparison with the other two methods used to estimate subindices cross-correlation, better explains the changes in the economy activity.

The occurrence of financial crises in recent decades has caused a lot of damage to the economy as well as economic enterprises in many countries. The Extreme Value Approach is a new approach to the phenomenon of financial crisis, which has been able to analyze the events that are less likely to occur but the damage caused by them is significant. In this study, we use the Extreme Value theory and Stochastic differential equations to find a new method for estimating the more precisely the value at risk. For this purpose, after estimating the parameters of the Stochastic differential equations, which includes the geometric Brownian motion, the geometric Brownian motion with the jump, the nonlinear GARCH model, and the Heston model, simulate the Monte Carlo simulations of future paths and then use peak over threshold approach, to estimate the value We at risk. The results of the simultaneous use of Stochastic differential equations and Extreme value theory ​​are compared with historical simulations and variance-covariance approaches for value at risk. The results of Back-test techniques on value at risk indicate the superiority of the Heston model in estimation of value at risk.

One of the most important actions on risk management is to obtain correct and rigorous information from the nature of the time series which are known as risk drivers. In this paper we introduce a model for interest free deposits using stochastic processes. To this end we use the geometric Brownian motion, jump-diffusion, Cox- Ingersol-Ross and mean-reversion models. Also to develop the approach we decompose the volatility of the time series into deterministic and stochastic parts and model the stochastic part only. The deterministic part is the sum of trend line and periodic cycles. We observe that after estimation of parameters and model calibration, the results are consistent with initial expectations which are as follows: The performance of the models increases with separation of deterministic and stochastic parts. Although at the same time the phenomenon of mean reversion and heavy tail is approved, but, Cox-Ingersol-Ross model show a better behavior than jump-diffusion model. Finally the man-reversion and Jump-diffusion models have better performance than other models.

Active management is one of the issues that is important in terms of violating effectiveness of financial markets financial markets. Because inefficient market, there is a potential to generate abnormal returns through active portfolio management. In many studies in this regard the reason for the surplus return compared to the baseline portfolio by minimizing the tracking error variance (TEV) in this regard, the risk of the entire portfolio is not taken into account. In this study, by using the differential evolution algorithm (DE) to optimize the active portfolio, with the goal of maximizing portfolio surplus returns compared to the standard portfolio, considering the risk of the entire portfolio from the calculated conditional risk value criterion (CVaR) based on the GARCH approach is used. The results of the portfolio consist of 14 stocks with a positive average yield from the beginning of 2011 to the end of June of 2017 from the top 50 stock exchanges on a monthly shows that subject to risk portfolio based on CVaR, causes better performance in the active optimization of the portfolio, based on backtesting method.

Paired trading is among the most well-known and oldest algorithmic trading systems. The efficiency and profitability of this system have been demonstrated in many studies conducted so far in financial markets. Paired trading is principally based on long-run equilibrium relationships or reverting to the mean characteristic. In recent years, a large number of studies have been conducted on algorithmic trading using machine learning.
In this research, the reinforcement learning method - an appropriate method for modeling and optimizing problems involving different long-run relationships - was used in order to select appropriate trading thresholds and time windows for the purpose of maximizing efficiency and minimizing negative risks in paired trading through adopting the co-integration approach. Results are obtained by applying a combination of reinforcement learning method and co-integration approach in paired trading.
Empirical results based on the intraday dataof paired stocks showed that the reinforcement learning method used to design trading systems in paired trading had significant advantages over the other methods in previous works.
A pair trading strategy with the proposed algorithm can be used as a neutral market strategy in all market conditions, including prosperity and recession, by investors and individual and institutionaltraders.Also, for future research, it is possible to consider transaction costs in a pair trading strategy.

This study examines the impact of information demand and supply in cyberspace on stock return and stock return variance. This research seeks to determine whether the information demand and supply can have a significant impact on stock return and stock return variance of companies listed on Tehran Securities Exchange. The study was conducted on a daily basis during the period 2012 to 2016 among 50 listed companies on TSE. In order to estimate the impacts, a Vector Auto-Regression (VAR) model is used in panel data. The predicted model is also estimated by the method of generalized moments. The estimated results show that information demand and supply have both been able to significantly affect the stock return of companies in the sample at a significant level of 5%. Furthermore, the results of the study indicate that the information supply and demand share on the stock return variance is increasing over time.

risk & return are two main factors that affect financial decisions. The trade off between risk & return create different investment strategies. In other words investment decisions are all based on risk & return. In this research we used multiperiod selection method in order to maximize investors utility. In this model we used not only variance but also higher order moment –skewness- for optimization.
For emprical test of the model we used return of first 50 companies stored by market capitalization in tehran stock exchange during 1386-1395. We used skewness
& transaction cost to introduce a moltipriod model in asset allocation to minimize variance of investors utility. Comparing the result of this model with markowitz model & simpel model considering investor preferences shows that based on performance evaluation criteria, the suggested model perform much better than the two other.