Detecting earnings management with neural networks

Höglund, Henrik

doi:10.1016/j.eswa.2012.02.096

Cited by 53 publications

(46 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, Vesanto (1997) suggested that self-organizing maps could be used for clustering purposes to enable the creation of local regressions for each node. Later, this procedure has also been used successfully in accounting studies (Höglund, 2012;Höglund, 2015;Haga et al, 2015). The input data in the SOM process with local regressions can be various combinations of the dependent variables, independent variables and other general variables.…”

Section: Self-organizing Mapsmentioning

confidence: 98%

Initial stage clustering when estimating accounting quality measures with self-organizing maps

Haga

Siekkinen

Sundvik

2015

Expert Systems with Applications

View full text Add to dashboard Cite

Section: Self-organizing Mapsmentioning

confidence: 98%

Initial stage clustering when estimating accounting quality measures with self-organizing maps

Haga

Siekkinen

Sundvik

2015

Expert Systems with Applications

View full text Add to dashboard Cite

“…Moreover, data mining aims to identify valid, novel, potentially useful and understandable correlations and patterns in earnings management data, and can be an alternative solution to classification problems. Related studies show that data mining has better predictive capability than conventional statistical methods in detecting earnings management, but it is not without limitations (Hsu and Pai 2013;Hoglund 2012;Malliaris and Malliaris 2014;Nan et al 2012;Tsai and Chiou 2009).…”

Section: Introductionmentioning

confidence: 97%

An alternative model for the analysis of detecting electronic industries earnings management using stepwise regression, random forest, and decision tree

Chen

2015

Soft Comput

View full text Add to dashboard Cite

This study attempts to diagnose the detecting electronic industries' earnings management by integrating suitable soft computing methods. Accounting earnings information is a very crucial element for corporate stakeholders to determine their stock prices and evaluate their supervision and management authority's performance, while it is also essential information for measuring corporate value. Hence, whether an enterprise can faithfully express its true economic meaning over its financial statements and how the management handles its earnings have turned out to be a popular issue widely discussed by researchers. Detecting public companies' earnings management is an important and challenging issue that has served as the impetus in many academic studies over the last few decades. Data mining technique and machine learning methods have also been commonly applied by accounting and financial personnel to other fields of studies. The study used the stepwise regression and random forest techniques to screen the variables in the first place, followed by adopting three kinds of decision trees including Chi-squared automatic interaction detector, classification and regression trees and C5.0 to establish a model and find out if the tested enterprise had extreme earnings manipulation. The results show that the proposed hybrid approach (RF+C5.0) has the optimal classification rate (the accuracy rate is 91.24 %) and the lowest occurrence of Type I error and Type II error. Also, as discovered from the rules set of the Communicated by V. Loia. final additional testing, an enterprise's operating cash flow, times interest earned ratio and previous period's discretionary accruals play a decisive role in affecting its extreme earnings management.

show abstract

“…Second, the performance of linear regression models depends on various assumptions such as absence of multicollinearity, and normally distributed residuals with zero mean and constant variance. However, these assumptions are not required with neural networks (Höglund 2015). Hence, based on the above analyses, the prediction power of the Probit regression was compared with MLP prediction results in the artificial neural networks according to the first and third hypothesis.…”

Section: Additional Analysesmentioning

confidence: 99%

Attitude toward auditing, marketing and corporate governance (An examination based in Parsons’ social action theory)

Mahdavi

Daryaei

2016

Int J Corporate Soc Responsibility

View full text Add to dashboard Cite

Auditing develops within a social context. On the basis of Parsons' social action theory, we examine whether auditors' attitude toward marketing activities influences the time balance between auditing and marketing activities and attitude toward the importance of corporate governance mechanisms. We use survey responses from 257 auditors in Iran. We conducted our analysis by applying a binary Probit regression and for additional analysis, we utilize neural networks. Attitude toward marketing has a positive significant relationship with balance time between auditing and marketing activities. And the attitude of auditors toward marketing has a positive significant relationship with attitude toward corporate governance. Also, the results showed a significant difference between industry expert auditors' attitude and other auditors toward marketing activities. Finally the results of this paper generally suggest that if artificial neural networks are employed in the prediction process, more reliable results will be achieved. The paper provides important insights into emerging issues and developments in auditing and marketing that have clear relevance to auditing research and practice. Drawing on our analytical framework, we provide directions for further opportunities for research of social theories and auditing.

show abstract

Detecting earnings management with neural networks

Cited by 53 publications

References 22 publications

Initial stage clustering when estimating accounting quality measures with self-organizing maps

Initial stage clustering when estimating accounting quality measures with self-organizing maps

An alternative model for the analysis of detecting electronic industries earnings management using stepwise regression, random forest, and decision tree

Attitude toward auditing, marketing and corporate governance (An examination based in Parsons’ social action theory)

Contact Info

Product

Resources

About