درخت حوزه‌های تخصصی

In this research, due to the importance of investing and especially investing in the stock market, we predicted the stock price return on the stock exchange through the Auto-Regressive Integrated Moving Average (ARIMA) and Recursive Neural Network (RNN) of long-short term memory (LSTM). Then, to reduce the risk of decision-making, we compared the predictive power of these two models to determine a better model. The research variable is the stock price of the top 20 (in market cap) companies on the stock exchange for the period of the 11th Feb 2015 to 22th Jan 2022. We considered the data of the last 10 days as experimental data and the previous data as educational data. Initially, we calculated the mean and standard deviation of the prediction error of both models; these criteria had less value for the LSTM recursive neural network model than the ARIMA model. To measure the significance of this difference in predictive power, we used Harvey, Liborne, and New Bold tests. The results showed that in predicting the stock prices of the top 20 companies of the stock exchange, the predictive power of the LSTM recursive neural network model was statistically and significantly higher than the ARIMA model which means better predition of stock prices and higher return for investors. In the end, it is believed that the LSTM model may have the best predictive ability, but it is greatly affected by the data processing.

In this paper, a new non-monotone line search is used in the diagonal discrete gradient bundle method to solve large-scale non-smooth optimization problems. Non-smooth optimization problems are encountered in many applications in fi-nance problems. The new principle causes the step in each iteration to be longer, which reduces the number of iterations, evaluations, and the computational time. In other words, the efficiency and performance of the method are improved. We prove that the diagonal discrete gradient bundle method converges with the pro-posed non-monotone line search principle for semi-smooth functions, which are not necessarily differentiable or convex. In addition, the numerical results confirm the efficiency of the proposed correction.

Stakeholders of an organization avoid undesirable outcomes caused by ignoring the risks. Various models and tools can be used to predict future outcomes, aiming to avoid the undesirable ones. Early warning models are one of the approaches that could help them in doing so. This study focuses on developing an early warning system using machine learning algorithms for predicting solvency in the insurance industry. This study analyses 23 financial ratios from Iranian general insurance companies listed on the Tehran Stock Exchange between 2015 and 2020. The model uses Decision Tree, Random Forest, Artificial Neural Networks, Gradient Boosting Machine and XGBoost algorithms, with Boruta as a feature selection method. The dependent variable is the solvency margin ratio, and the other 22 ratios are the independent variables, which Boruta reduces to 7 variables. Firstly, the performance of the machine learning models on two datasets, one with 22 independent variables and one with 7, is compared based on RMSE values. The XGBoost algorithm performs the best on both data sets. Additionally, the study predicts the 2020 values for 19 insurance companies, performs stage classifications, and compares actual stages to predicted stages. In this analysis, Random Forest has the best estimate accuracy on both data sets, while Gradient Boosting Machine has the best estimate accuracy on the Boruta data set. Finally, the study compares the machine learning models' results in terms of capital adequacy classification, where Random Forest performs the best on both data sets, and Gradient Boosting Machine on the Boruta data set.

One of the most important factors of the development of an economy is the mergers or acquisitions (M&A) at the level of its active companies such as insurance companies. The main purpose of this study is to examine the efficiency of merger and acquisition before doing this process in the insurance industry using network data envelopment analysis and can select the companies that potentially facilitate achieving the purposes of the merger and acquisition process and improve of this action. For this purpose, in this study, first the efficiency of 20 insurance companies was measured through the Modified Slack-Based Measure (MSBM) in the two-stage data envelopment analysis approach during three years 2017, 2018 and 2019. Then, considering the calculated efficiency, Asia Insurance Company, Parsian, Dey, Pasargad, Kowsar and Taavon, which have had efficient performance in the last three years, were excluded from the calculations and other companies were selected for M&A . After ensuring that no monopoly is considered via Herfindahl- Hirschman Index, M&A is performed and then the overall efficiency was measured and it was divided into three parts: technical, harmony and scale. The results showed that the two consolidations Dana-Mihan and Dana-Sina had the best efficiency and the three consolidations Alborz-Mellat, Sina-Arman and Sina-Sarmad had the lowest efficiency and potential for the highest improvement. Calculations also showed that if the scale effect in the composition is greater than 1, then the coordination effect is smaller than 1 and the inverse relationship are not necessarily satisfied.

This paper addresses the absence of a suitable criterion for measuring information asymmetry between managers forecasting earnings and analysts forecasting earnings through statistical methods. Besides, this paper aims to provide a model of information asymmetry, emphasizing the role of financial and managerial criteria. This is applied qualitative and quantitative research (mixed method). The library method is used to prepare and formulate theoretical bases. In addition, the field method is used for collecting data to measure and identify indices and modeling. Factor analysis was used to analyze the data, following identifying the dimensions and variables of financial and managerial criteria of information symmetry to eliminate extraneous factors and classify. The following five main dimensions were determined, including corporate profit forecast, corporate governance, capital market, capital return, and management characteristics of the company. Then, the modeling was done using fuzzy mathematics through triangular numbers, Mamdani implication, and center of gravity methods. The final results of the study of the company listed on the Tehran Stock Exchange show that the level of information symmetry in the range of zero to 100 equals 55.1, to predict the company's profit is 48.54; corporate governance is 56.95; the capital market is 1/59; capital return is 61.07, and managerial characteristics of the company are 67.84. Finally, we examined the factors affecting the information asymmetry obtained from fuzzy neural networks. The findings show a higher prediction accuracy of fuzzy neural network methods than other related prediction methods.

In traditional Data Envelopment Analysis (DEA) techniques, in order to calculate the efficiency or performance score, for each decision-making unit (DMU), specific and individual DEA models are designed and resolved. When the number of DMUs are immense, due to an increase in complications, the skewed or outdated, calculating methods to compute efficiency, ranking and …. may not prove to be economical. The key objective of the proposed algorithm is to segregate the efficient units from that of the other units. In order to gain access to this objective, effectual indexes were created; and taken to assist, in regards the DEA concepts and the type of business (under study), to survey the indexes, which were relatively operative. Subsequently, with the help of one of the clustering techniques and the ‘concept of dominance’, the efficient units were absolved from the inefficient ones and a DEA model was developed from an aggregate of the efficient units. By eliminating the inefficient units, the number of units which played a role in the construction of a DEA model, diminished. As a result, the speed of the computational process of the scores related to the efficient units increased. The algorithm designed to measure the various branches of one of the mercantile banks of Iran with financial indexes was implemented; resulting in the fact that, the algorithm has the capacity of gaining expansion towards big data.