نوع مقاله : مقاله پژوهشی
نویسندگان
1 دانشجوی دکترا، رشته حسابداری، دانشکده حسابداری، دانشگاه آزاد اسلامی، واحد ارومیه، رومیه، ایران
2 دانشیار گروه حسابداری، دانشکده حسابداری، دانشگاه آزاد اسلامی، واحد ارومیه، رومیه، ایران
3 استادیار گروه حسابداری، دانشکده حسابداری، دانشگاه آزاد اسلامی، واحد ارومیه، رومیه، ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
The purpose of the study was to design a stock valuation model based on capital market indicators using data mining methods. In this article, structural equation modeling was used to investigate the effect of capital market indicators on stock value. The results showed that the capital market indicators have a significant effect on the stock value and 52.7% of the stock value was explained by the fluctuations of the capital market indicators. In the next step, in order to test the hypothesis of the research, the accuracy of 32 machine learning models was first compared in order to predict the stock value, and the results showed that the C5 model has a higher prediction accuracy than other machine learning models. Further, in order to increase the accuracy and reduce the error of the C5 model, boosting and feature selection validation techniques were used, and the results showed that the superior model (C5) has a significant increase in accuracy and a noticeable decrease in error. Also, modeling was done separately for capital market indicators and the results showed that cash indicators are more accurate than other indicators in order to predict stock value. The purpose of the study was to design a stock valuation model based on capital market indicators using data mining methods. In this article, structural equation modeling was used to investigate the effect of capital market indicators on stock value. The results showed that the capital market indicators have a significant effect on the stock value and 52.7% of the stock value was explained by the fluctuations of the capital market indicators. In the next step, in order to test the hypothesis of the research, the accuracy of 32 machine learning models was first compared in order to predict the stock value, and the results showed that the C5 model has a higher prediction accuracy than other machine learning models. Further, in order to increase the accuracy and reduce the error of the C5 model, boosting and feature selection validation techniques were used, and the results showed that the superior model (C5) has a significant increase in accuracy and a noticeable decrease in error. Also, modeling was done separately for capital market indicators and the results showed that cash indicators are more accurate than other indicators in order to predict stock value.
کلیدواژهها [English]