DOAJ (DOAJ: Directory of Open Access Journals), Apr 30, 2022
Objective: In this study, a market liquidity prediction model is proposed for the Tehran Stock Ex... more Objective: In this study, a market liquidity prediction model is proposed for the Tehran Stock Exchange (TSE) by identifying the factors affecting liquidity. Methods: Based on the data of 154 Tehran Stock Exchange (TSE)-listed companies for the 2009-2020 period, the values of 23 factors were extracted and divided into two clusters. The partial least squares structural equation modeling (PLS-SEM) technique was employed to validate the variables extracted through the evaluation criterion and to determine their power to explain changes. Results: The relationships among the variables were evaluated by machine learning models. The results indicated the 10 variables of abnormal cash flow, abnormal discretionary expenses, accrual estimation error, the difference between fulfilled and expected working capitals, free float, auditor's tenure, audit fees, auditor's market share, conservatism, and change of auditor to have the greatest effect on clustering. Finally, the best machine learning model was selected through training and testing. Applying the logistic regression model showed that for the calculated value of a dependent variable greater than or equal to 3.391, the illiquidity of the company's shares is definite, and for the calculated value of the dependent variable less than 3/391, the liquidity of shares of the company is definite. Finally, the best machine learning model was selected through training and testing. Conclusion: Based on library studies, 89 different liquidity criteria have been used around the world in the studies on the subject of liquidity and various classifications, including measures with more or less frequency and one-dimensional or multidimensional measures. There is less agreement on the best measure and the correlation among most of these measures indicating that the use of an inappropriate measure may lead to incorrect conclusions. Using Minitab software, the dependent variable was compared with 5 commonly used criteria (measures) known in library studies (Liu measure, Amihud illiquidity measure, zero measure, number of trading day measure, and trading volume measure). The results confirm the statistically significant difference between the widely used and newly obtained measures. It should be noted that the dependent variable was extracted using non-supervisory patterns in machine learning software and a statistically significant difference between the widely used criteria and the obtained variable was proved. Thus, the resulting variable is a criterion for liquidity. According to the results, the independent variables explain more than 72 percent of the changes in liquidity. Moreover, the neural network model was more capable of prediction than the other machine learning models. In fact, it was proved as the best liquidity prediction model with 99.32 percent of the fitness accuracy.
<strong>Objective:</strong> The main objective of this paper is to investigate the re... more <strong>Objective:</strong> The main objective of this paper is to investigate the relationship between predicted financial distress and earnings management approaches. <br /><strong>Methods: </strong>We predict financial distress for 312 stock market listed and out-listed companies from 2006 to 2015 using C5 decision tree model. Then the relationship between financial distress prediction and earnings management approaches was observed using multivariate linear regression model (structural equation modeling approach). <br /><strong>Results:</strong> The results showed that there is a significantly negative relationship between predicted financial distress and the first actual activity earnings management index, while there was a significantly positive relationship between the predicted financial distress and the second actual activity earnings management index and the accrual earnings management index. <br /><strong>Conclusion:</strong> We concluded that distressed companies in comparison with other companies will be able to manipulate their earnings significantly by increasing operating cash flows and accrual items and also by decreasing costs. It was also found that earnings management tools are influenced by the type of industry and the predicted financial distress and earnings management tools affected each other through the cause and effect relationship.
The main purpose of this paper is to investigate financial distress prediction models accuracy an... more The main purpose of this paper is to investigate financial distress prediction models accuracy and earnings management approaches. Thus, primarily model was selected by comparing financial distress prediction models and its relation was analised through earnings management tools. In order to predict financial distress the comparison of machine learning and statistical models were considered for 312 listed companies at the Tehran Stock Exchange (TSE) during 2006 to 2015 and the result determined by comparing mean test shows that machine learning models can predict financial distress more accuracy than statistical models. Then, the relation between the best model resulted from previous section and earnings management tools was investigated by multiple linear regressions and the result shows that relation between financial distress prediction and operating cash flows earnings management was negative and significant and this relation with earnings management for manufacturing costs and ...
DOAJ (DOAJ: Directory of Open Access Journals), Apr 30, 2022
Objective: In this study, a market liquidity prediction model is proposed for the Tehran Stock Ex... more Objective: In this study, a market liquidity prediction model is proposed for the Tehran Stock Exchange (TSE) by identifying the factors affecting liquidity. Methods: Based on the data of 154 Tehran Stock Exchange (TSE)-listed companies for the 2009-2020 period, the values of 23 factors were extracted and divided into two clusters. The partial least squares structural equation modeling (PLS-SEM) technique was employed to validate the variables extracted through the evaluation criterion and to determine their power to explain changes. Results: The relationships among the variables were evaluated by machine learning models. The results indicated the 10 variables of abnormal cash flow, abnormal discretionary expenses, accrual estimation error, the difference between fulfilled and expected working capitals, free float, auditor&#39;s tenure, audit fees, auditor&#39;s market share, conservatism, and change of auditor to have the greatest effect on clustering. Finally, the best machine learning model was selected through training and testing. Applying the logistic regression model showed that for the calculated value of a dependent variable greater than or equal to 3.391, the illiquidity of the company&#39;s shares is definite, and for the calculated value of the dependent variable less than 3/391, the liquidity of shares of the company is definite. Finally, the best machine learning model was selected through training and testing. Conclusion: Based on library studies, 89 different liquidity criteria have been used around the world in the studies on the subject of liquidity and various classifications, including measures with more or less frequency and one-dimensional or multidimensional measures. There is less agreement on the best measure and the correlation among most of these measures indicating that the use of an inappropriate measure may lead to incorrect conclusions. Using Minitab software, the dependent variable was compared with 5 commonly used criteria (measures) known in library studies (Liu measure, Amihud illiquidity measure, zero measure, number of trading day measure, and trading volume measure). The results confirm the statistically significant difference between the widely used and newly obtained measures. It should be noted that the dependent variable was extracted using non-supervisory patterns in machine learning software and a statistically significant difference between the widely used criteria and the obtained variable was proved. Thus, the resulting variable is a criterion for liquidity. According to the results, the independent variables explain more than 72 percent of the changes in liquidity. Moreover, the neural network model was more capable of prediction than the other machine learning models. In fact, it was proved as the best liquidity prediction model with 99.32 percent of the fitness accuracy.
<strong>Objective:</strong> The main objective of this paper is to investigate the re... more <strong>Objective:</strong> The main objective of this paper is to investigate the relationship between predicted financial distress and earnings management approaches. <br /><strong>Methods: </strong>We predict financial distress for 312 stock market listed and out-listed companies from 2006 to 2015 using C5 decision tree model. Then the relationship between financial distress prediction and earnings management approaches was observed using multivariate linear regression model (structural equation modeling approach). <br /><strong>Results:</strong> The results showed that there is a significantly negative relationship between predicted financial distress and the first actual activity earnings management index, while there was a significantly positive relationship between the predicted financial distress and the second actual activity earnings management index and the accrual earnings management index. <br /><strong>Conclusion:</strong> We concluded that distressed companies in comparison with other companies will be able to manipulate their earnings significantly by increasing operating cash flows and accrual items and also by decreasing costs. It was also found that earnings management tools are influenced by the type of industry and the predicted financial distress and earnings management tools affected each other through the cause and effect relationship.
The main purpose of this paper is to investigate financial distress prediction models accuracy an... more The main purpose of this paper is to investigate financial distress prediction models accuracy and earnings management approaches. Thus, primarily model was selected by comparing financial distress prediction models and its relation was analised through earnings management tools. In order to predict financial distress the comparison of machine learning and statistical models were considered for 312 listed companies at the Tehran Stock Exchange (TSE) during 2006 to 2015 and the result determined by comparing mean test shows that machine learning models can predict financial distress more accuracy than statistical models. Then, the relation between the best model resulted from previous section and earnings management tools was investigated by multiple linear regressions and the result shows that relation between financial distress prediction and operating cash flows earnings management was negative and significant and this relation with earnings management for manufacturing costs and ...
Uploads
Papers by ali ashtab