مجله راهبرد مدیریت مالی
سال یازدهم شماره 3 (پیاپی 42، پاییز 1402)

The current paper has investigated the comparison of the accuracy of machine learning and statistical models in predicting cash holdings using a set of financial and economic variables. Research methodology can be divided into three stages: selection of data set and variables, modeling and estimation. The statistical sample of the current research is the Tehran Stock Exchange, where the data of 173 companies have been analyzed during the period of 2010-2021. The results indicate the high accuracy of the symbolic regression model using the genetic algorithm with an accuracy factor of 71% in this field. After that, Gradient Boosted Trees, MARS regression, neural network and XGboost models were evaluated as the most accurate models for prediction. Finally, the KNN model showed the weakest prediction accuracy. Also, although the statistical models showed low prediction accuracy, they obtained a higher accuracy coefficient from some machine learning models. Also, the results showed that the use of Lasso regression improves the accuracy of statistical models and some machine learning models. This research can add new angles of cash retention forecasting techniques in financial studies, which have not been investigated in financial literature so far.

Volatility in the financial markets is one of the most important variables in investment decisions, securities and derivatives pricing, risk management, regulation and monetary policy. In addition, the volatility of the financial markets plays an important role in the economy of the country through the creation or diminution of public confidence.This paper examines the relationship between order imbalance and stock price volatility. Order imbalance refer to difference between numbers of buy-sell orders as well as their volume.To measure this volatility, we extract 5-minute and 10-minute intraday data and calculate realized volatility using them. Our research sample was selected from listed companies in Tehran Stock Exchange and Iran Fara Bourse for the period 1397 to 1399. Panel regression is used to examine research model.Our findings show that there is significant relationship between order imbalance and realized volatility. In the other hand we find that the effect of number of buy/sell order on good/bad volatility is asymmetric.

Similar to other main markets in an economy the stock market is also affected by various shocks that can negatively or positively affect the stock market and subsequently the national economy. Despite the fact that the economies of the Middle East are generally dependent on oil revenues, the change in the views of their politicians in recent decades and moving towards the replacement of incomes from other economic activities, such as capital market incomes instead of traditional income channels, has caused to pay special attention to the impact of different economic variables on these markets. In the meantime, the way the stock markets of the Middle East economies respond to various shocks, especially the shocks of competing markets such as the gold market and the foreign exchange market, has gained so importance. Therefore, the aim of the present study is to investigate the response of stock market returns of selected Middle Eastern countries to the shocks of parallel markets such as the foreign exchange market and the gold market as two competing markets. The estimated panel vector autoregression (PVAR) approach was used to estimate the model and impulse response functions (IRF) to extract the effect of shocks in the period from 2010 to 2021 using monthly data. The results show the positive response of the Middle East stock markets to the currency shock and the gold price shock. Increase in the exchange rate and the gold price lead the returns of the stock markets in the Middle East economies to increase at the first month. Moreover, the results of the variance decomposition (VDC) reveal that the most explanation in the variation of the forecast error variance is caused by the gold price variable and the exchange rate stands as the second.

Pyramidal and network ownership structures, which give ultimate owners greater control rights over companies than cash flow rights, are prevalent in the Iranian stock market. Given the complex shareholding networks and significant changes in the ownership structures of large Iranian firms over the past two decades, this study aims to examine the relationship between ownership structure and company performance. Four measures are used to analyze ownership structure: cash flow right of the largest shareholder, wedge between control right and cash flow right of the largest shareholder, difference in cash flow rights of the two largest shareholders, and type of ownership. The study investigates their relationship with the performance and stock returns of 261 listed companies during the period of 2015 to 2020. The results indicate a positive and significant association between the cash flow right of the largest shareholder and firm performance, but only when the largest shareholder owns at least 15% of the company's shares. For firms with only one owner and less than 50% in control rights, there is no significant correlation between the cash flow right of the largest shareholder and performance. The study also reveals that ownership by insurance companies has a positive correlation with firm performance, while quasi-governmental ownerships have a negative correlation with performance.

Optimizing the investment portfolio is one of the vital issues in investment management. The various fluctuations of the financial markets and the uncertainty of the parameters make using classical models a severe challenge. Therefore, the optimization of financial models in conditions of uncertainty to adapt to the real world has been the focus of researchers. In the present research, a hybrid optimization model has been developed by applying data envelopment analysis and robust programming to assess risk with uncertain inputs and outputs. The statistical population of the research was extracted from the Coin Marketcap portal, where the updated data of the adjusted price of 37 selected top cryptocurrencies was used to estimate the risk and create an optimal portfolio. A two-step approach for selecting and optimizing the stock portfolio, increasing the stability of the investment process, and comprehensive evaluation of stocks based on financial criteria is proposed. In the first stage, the performance assessment of the selected stocks is done using the robust programming-data envelopment analysis (RDEA) method. Then, in the second phase, the investment amount in eligible stocks is determined using the half-variance average and absolute standard deviation models. The performance of the proposed approach is evaluated in a case study of cryptocurrency data with increasing uncertainty. The comparative results of robust peer models with two risk measures show that the mean semi-variance model performs better in choosing and optimizing the investment portfolio.

Earnings and earnings per share information are metrics that are considered important by many users; Therefore, companies try to attract investors with the most accurate forecast of earnings per share. On the other hand, despite the various methods of forecasting earnings, accurate forecasting of earnings per share in the financial field is not easy and most researchers are trying to determine the best way to forecast earnings; Therefore, the main purpose of this study is to investigate the accuracy of support vector machine based on genetic algorithm compared to common linear methods in forecasting earnings per share. For this purpose, samples consisting of 100 companies listed on the Tehran Stock Exchange during the years 2008-2019 have been studied. In order to achieve the objectives of the research, first by studying previous research in the field of earnings forecasting, 14 financial ratios affecting earnings forecasting have been selected. Then, in order to provide a model for predicting the profitability of companies, a combined model of support vector machine based on genetic algorithm, support vector machine and linear regression is compared. The results showed that the hybrid model of support vector based on genetic algorithm is much better in predicting the trend of earnings per share and has a higher accuracy compared to the model of support vector based on kernel functions and linear regression method. Thus, with the development of the support vector machine model based on the genetic algorithm, the model training error is reduced to 0.036 and the accuracy of the model is increased up to 75%.

Entrepreneurship includes all activities and actions related to understanding opportunities and establishing an organization to take advantage of these opportunities. The present study is of the mixed-exploratory type which has been done using Q methodology. This study was conducted with the participation of nine professors familiar with the subject of research as well as banking experts. The discourse space of the present study was collected from various sources and after evaluating and summarizing the discourse space, 35 phrases were selected for the sample. Then, after collecting the data obtained from Q sorting, this information was analyzed by the Q factor analysis method. Distribution analysis showed that three distinct mental patterns could be identified among the participants in the research on subjective patterns of identifying entrepreneurial opportunities, which together explained about 93% of the total variance. These three mental models were named organizational strategy, entrepreneurial policy, and value creation for customers, respectively.

Today, the development of a comprehensive corporate social responsibility reporting in order to create transparency and accountability in capital markets, attracted considerable attention. Therefore, the purpose of the present study is to investigate the relationship between corporate social responsibility reporting and stock liquidity and study the moderating effect of external monitoring on this relationship. The present study is concerned with examining the association between social responsibility and stock liquidity as well as exploring the moderating effect of external monitoring on this relation. A sample of 87 firms listed in Tehran Stock Exchange during 2013 to 2018 is examined. To analyze data and test hypotheses, the multivariate regression model based on panel data is used. The results show that there is a significant positive relationship between corporate social responsibility reporting and stock liquidity. In addition, the results indicate that external monitoring played a moderating role in the relationship between corporate social responsibility and stock liquidity and exacerbated the positive relationship between them. Research findings can be useful for investors, the Securities and Stock Exchange organization and other stakeholders for decision making.

One of the most important causes of banking system problems is not paying enough attention to credit risk. Ignoring the creditworthiness of applicants and mandatory facilities has left banks with a significant amount of problem assets and a large number of non-current facilities and has severely reduced their ability to finance. Intelligent methods such as multivariate switching model, due to the behavior based on multiple analysis, make it possible to find appropriate answers to predict the amount of risk. The purpose of this study is to model the credit risk of some Iranian banks using the Markov-Switching method. In order to prevent potential losses of banks, it is important to study the variables that have a significant impact on creating high-risk and critical conditions. This can be modeled through the Markov dual-regime model, which is a useful way to describe the process by which variables escape in a series of states at a continuous time being measured. Therefore, in this paper, by analyzing independent variables such as micro and macroeconomic variables, financial factors, external shocks and financial distress index using multivariate switching method to identify, score and determine the impact of each of the independent variables in credit risk control and consequently credit risk forecast is considered in banks. In this regard, three hypotheses were determined and the annual data of the member banks of the Tehran Stock Exchange in the period 2011 to 2020 were used to test the hypothesis. The results of experiments in MATLAB software show the proper performance of risk prediction accuracy of the method based on multivariate Markov switching.

Investors have heterogeneous beliefs about the value of a company. Investor homogenization is a very important assumption in the efficient market hypothesis. However, Many anomalies often occur due to too much distance between theory and reality. In this regard, the theoretical literature focuses more on the movements resulting from the beliefs of investors or the heterogeneity of investors. Stock price movements have been considered by researchers and experts as one of the most common anomalies, which indicates the movement caused by differential beliefs of investors or investor heterogeneity. The purpose of this paper is to investigate the effect of investor heterogeneity on the concurrence of stock prices and stock returns of companies. to investigate the issue, based on multivariate regression, data of 96 companies listed on the Tehran Stock Exchange during the period 2011-2018 were collected from the new Rahavard software, financial statements and the official website of the Tehran Stock Exchange and used to test research hypotheses. According to the research findings, investors who have high heterogeneity in their investments increase the synchronization of stock prices and stock returns. Heterogeneous beliefs of investors affect the concurrence of stock prices and stock returns of companies.