Modelling and Predicting Earnings Quality Using Decision Tree and Support Vector Machine

Subject Areas :

Loghman Hatami Shirkouhi ¹ , Soghra Barari Nokashti ² , Maryam Ooshaksarae ³

1 - PhD student, Accounting Department, Rasht Branch, Islamic Azad University, Rasht, Iran
2 - Assistant Professor, Department of Accounting, Rasht Branch, Islamic Azad University, Rasht, Iran
3 - Assistant Professor, Department of Industrial Management, Rasht Branch, Islamic Azad University, Rasht, Iran

Received: 2023-08-29 Accepted : 2023-12-06 Published : 2023-11-22

Keywords: Support vector machine, Conservatism, Accruals, earnings quality, Decision tree,

Abstract :

Earnings and its quality are one of the most important decision-making com-ponents for users. Therefore, earnings quality prediction is very important for investors and other stakeholders. To this aim, decision tree and support vec-tor machine (SVM) were used to predict earnings quality. The statistical population of the study included companies listed in Tehran Stock Exchange from 2011 to 2021 for 10 years. After screening, 113 companies and 1130 observations were selected as statistical samples. In order to identify and predict earnings quality, indicators related to corporate governance (board independence, audit committee independence, organizational ownership), dividend policy, debt financing, and conservatism were considered as inde-pendent variables and discretionary accruals quality representing profit quali-ty index was considered as a dependent variable. Data analysis was done according to CRISP-DM data mining standards and implementation of four decision tree algorithms including CHAID, C5.0, C&R, QUEST, and SVM. As the results showed, board independence had the greatest effect on earn-ings profit quality. Considering the accuracy value for the created SVM, which is equal to 98.5%, it indicates the high capability of this method to predict earnings quality.