Advances in Mathematical Finance and Application (AMFA)

Stock market forecasting has attracted so many researchers and investors that many studies have been done in this field. These studies have led to the development of many predictive methods, the most widely used of which are machine learning-based methods. In machine learning-based methods, loss function has a key role in determining the model weights. In this study a new loss function is introduced, that has some special features, making the investing in the stock market more accurate and profitable than other popular techniques. To assess its accuracy, a two-stage experiment has been designed using data of Tehran Stock market. In the first part of the experiment, we select the most accurate algorithm among some of the well-known machine learning algorithms based on artificial neural network, ANN, support vector machine, SVM. In the second stage of the experiment, the various popular loss functions are compared with the proposed one. As a result, we introduce a new neural network using a new loss function, which is trained based on genetic algorithm. This network has been shown to be more accurate than other well-known and common networks such as long short-term memory (LSTM) for both train and test data.

A stock exchange is an entity which provides ‘‘trading’’ facilities for stock brokers and traders to trade stocks and other securities. How to invest in stock exchange is one of the important issues in investment, and one of the factors that can help investors in the process of investment is the efficiency of the corporation under consideration. Data envelopment analysis is a mathematical methodology that has been widely applied to assess the performance of banks and financial institutes. The main feature of this method is that this methodology evaluate firms by considering multiple inputs and outputs. Conventional DEA models consider each firms as black box and don’t note into the inner activities. Two-stage data envelopment analysis has been researched by a number of authors that evaluate each firm by considering the inner operations. This paper proposes a new two stage BAM model and further evaluates the banks and financial institutes in Tehran stock exchange by considering the financial ratios. Conventional DEA models consider each firms as black box and don’t note into the inner activities. Two-stage data envelopment analysis has been researched by a number of authors that evaluate each firm by considering the inner operations. This paper proposes a new variant of two stage DEA models and further evaluates the banks and financial institutes in Tehran stock exchange by considering the financial ratios.

Efficient use of assets in agriculture is a goal for policy-makers and farmers. Agricultural input resources are scarce therefore optimum use of inputs in different agricultural operations is important. Mathematical programming technique such as data envelopment analysis (DEA) is a well-known approach for estimation efficiency of agricultural DMUs. In this study, efficiency of kidney bean production in twelve provinces of Iran has been studied. Inputs were cost of tillage, planting, cultivation, harvesting and land. Output included total production value of kidney bean. Land cost is a non-controllable variable. Therefore; a non-discretionary DEA approach was applied to estimate efficiency of kidney bean production. The average value of technical efficiency score of kidney bean production was 0.74. Results showed that 58 percent of DMUs were efficient and the rest were inefficient. In optimum condition based on the proposed model, tillage, planting, cultivation and harvesting costs is decreased by 34.48%, 11.92%, 27.87% and 7.27%, respectively, without decreasing kidney bean production level.

In the current world, the debate on the reinstatement and reuse of consumer prod-ucts has become particularly important. Since the supply chain of the closed loop is not only a forward flow but also a reverse one; therefore, companies creating integ-rity between direct and reverse supply chain are successful. The purpose of this study is to develop a new mathematical model for closed loop supply chain net-work. In the real world the demand and the maximum capacity offered by the sup-plier are uncertain which in this model; the fuzzy theory discussion was used to cover the uncertainty of the mentioned variables. The objective functions of the model include minimizing costs, increasing revenues of recycling products, increas-ing cost saving from recycling and environmental impacts. According to the NP-hard, an efficient algorithm was suggested based on the genetic Meta heuristic algo-rithm to solve it. Twelve numerical problems were defined and solved using the NSGA-II algorithm to validate the model

The main criterion in investment decisions is to maximize the investors utility. Traditional capital asset pricing models cannot be used when asset returns do not follow a normal distribution. For this reason, we use capital asset pricing model with independent and identically asymmetric power distributed (CAPM-IIAPD) and capital asset pricing model with asymmetric independent and identically asymmetric exponential power distributed with two tail parameters(CAPM-AIEPD) to estimate return and risk. When the assumption of normality is violated, the first and second moments lose their efficiency in optimization and we need to use the third and fourth moments. For the first time, we propose independent and identically asymmetric exponential power distributed with two tail parameters. Then, we use higher moments optimization with unequal weights to optimize portfolios. The results indicate that capital asset pricing model with independent and identically asymmetric power distributed (CAPM-IIAPD) is better than asymmetric independent and identically asymmetric exponential power distributed with two tail parameters(CAPM-AIEPD) to estimate return and risk. Adjusted Sharp ratio in portfolio optimization in second moments are higher than others. Adjusted returns to risk in third and fourth moments in the CAPM-IIAPD model significantly differ from the CAPM-AIEPD model and have a better performance.

The most common starting point for investors when buying a stock is to look at the trend of price changes. In recent years, different models have been used to predict stock prices by researchers, and since artificial intelligence techniques, including neural networks, genetic algorithms and fuzzy logic, have achieved successful re-sults in solving complex problems; in this regard, more exploitation Are. In this research, the prediction of stock prices of companies accepted in the Tehran Stock Exchange using artificial intelligence algorithm (non-sensory-parametric support vector regression algorithm in linear and nonlinear mode) has been investigated. The results of the research show that the PINSVR algorithm in nonlinear mode has been able to predict the stock price over the years, rather than linear mode.

Managers engage in income smoothing either to communicate private information about future earnings to investors (informativeness hypothesis) or to distort financial performance for opportunistic purposes (opportunism hypothesis). Business cycles and the monitoring role of institutional ownership may affect the earnings informativeness of income smoothing. The purpose of this research is to examine the effect of business cycles and institutional ownership on the earnings informativeness of income smoothing. 140 firms listed on the Tehran Stock Exchange are selected as the sample over the period 2010-2016. The results showed that, during recession, income smoothing does not effectively communicate information about future earnings and thus earnings are less informative. Moreover, higher levels of institutional ownership are associated with a decrease in their monitoring role and decrease in the earnings informativeness of income smoothing. Finally, the results suggested that the relationship between institutional ownership and the earnings informativeness of income smoothing is not significantly affected by business cycles.

For many investors, it is important to predict the future trend of abnormal stock returns. Thus, in this research, the abnormal stock returns of the listed companies in Tehran Stock Exchange were tested since 2008- 2017 using three hypotheses. The first and second hypotheses examined the non-linearity and non-randomness of the abnormal stock returns ′ trend around the release date of annual financial statements, respectively. While, the third hypothesis tested the potential of the chaos model in explaining future abnormal returns based on the past abnormal returns around the release date of the annual financial statements. For this pur-pose, BDS, Teraesvirta Neural Network, and White Neural Network tests were used to investigate its non-linearity. In addition, Lyapunov exponent, correlation dimension, Dickey-Fuller, and Hurst exponent tests were used for testing non-randomness and the fitness of AR, SETAR, and LSTAR models to determine the optimal model in explaining the abnormal returns utilizing R software. Results of these tests represented a non-linear and non-random process and chaos in the abnormal stock returns, implying the predictability of abnormal stock returns. Also, among three used chaos models, the LSTAR model had lower error and more predictability than the other two models.

Stock price crash risk has a significant impact on investors, creditors, managers, and shareholders, so the prediction of this phenomenon is a very important issue in investment and risk management decisions. This research investigates the effect of business strategy and stock price synchronicity on stock price crash risk. Following Bentley et al.[2], composite strategy score has been used to proxy for an organization’s business strategy, expanded market model regression following Chen et al. [3] to measure the firm-specific crash risk, and R2 method of Johnstone [14] to calculate the stock price synchronicity. In order to achieve this point, financial information of 171 companies that are listed on Tehran stock exchange have been selected during the time period of 2013 to 2018, and data was analysed using regression model. According to the results, companies with defender (analyser and prospector) business strategy are less (more) prone to future crash risk. Moreover, results show that stock price syn-chronicity has positive effect on stock price crash risk, while in companies with analyser business strategy it can reduce the stock price crash risk. The interactive effect of business strategy and stock price synchronicity on stock price crash risk in companies with prospector and defender business strategy is not significant. Other findings suggest that Institutional ownership has positive, and company’s age has negative effect on stock price crash risk.

One of the challenging issues for investors and professionals is appropriate models to evaluate financial situation of the firms. In this regard, many models have been extracted by researchers using different financial ratios to resolve these issues. However, choosing a model based on the conditions and users’ needs is complex. The main objective of this study is to identify the effect of contingency variables on the firms’ financial performance forecasting models. The statistical population of the research includes all firms listed in Tehran Stock Exchange during the period 2011-2018, among which 154 firms were selected. The research data were collected from firm's financial statements and other source. Multiple Discriminant Analysis and Logit Regression model were used to test the research hypotheses. According to the results of discriminant analysis, environmental uncertainty and firm size positively improve the predictive power of the firm's financial performance, and business strategy and business competition don’t improve the predictive power of the firm's financial performance. Also, the results of logit regression indicated that environmental uncertainty, business strategy, and firm size improve predictive power of the firm's financial performance; but, business competition don’t improve predictive power of the model. The results of comparing the two methods showed that the Discriminant analysis method outperformed the logistic regression method.

both academic and auditing firms have been searching for ways to detect corporate fraud. The main objective of this study was to present a model to detect financial reporting fraud by companies listed on Tehran Stock Exchange (TSE) using genetic algorithm. For this purpose, consistent with theoretical foundations, 21 variables were selected to predict fraud in financial reporting that finally, using statistical tests, 9 variables including SALE/EMP, RECT/SALE, LT/CEQ, INVT/SALE, SALE/TA, NI/CEQ, NI/SALE, LT/XINT, and AT/LT were selected as the potential financial reporting fraud indexes. Then, using genetic algorithm, the final model of fraud detection in financial reporting was presented. The statistical population of this study included 66 companies including 33 fraudulent and 33 non-fraudulent companies from 2011 to 2016. The results showed that the presented model with the accuracy of 91.5% can detect fraudulent companies. These findings extend financial statement fraud research and can be used by practitioners and regulators to improve fraud risk models.

Managers are responsible for providing financial statements and they might try to make a good picture of their firm's conditions. Therefore, they try to delay the disclosure of bad news and release the good news as soon as possible. The ten-dency of managers toward hiding bad news increases the stock price crash risk. The protection of investor is one of the factors that can prevent from falling stock price, because it restricts the managers and majority shareholders in frauding and hiding bad news. Thus, the main purpose of the present research is to study the effect of investor protection on future stock price crash risk. In this research, 89 companies from listed companies in Tehran Stock Exchange during 2011-2017 were tested. The results obtained from the research's hypothesis test showed that protecting the rights of investors has a negative effect on the stock price crash risk. In fact it can be concluded that with the increase of the investor protection, the firms are obligated to disclose the high-quality accounting information and present more transparent financial reporting, as a result, the information asym-metry will be reduced and by creating a flow of information between the manag-ers and the investors and thus failure to accumulate bad news in the company, the risk of the stock price crash will be also reduced.