[Home ] [Archive]   [ فارسی ]  
:: Main :: About :: Current Issue :: Archive :: Search :: Submit :: Contact :: Register ::
:: Volume 1, Issue 2 (6-2022) ::
3 2022, 1(2): 31-41 Back to browse issues page
Comparison of the Prediction Accuracy of Earning Manipulation in Development of the Beneish Model by combination of Artificial Neural Network and Imperialist Competition and Particle Swarm Optimization Algorithms
Abstract:   (45 Views)
According to Beneish (1999), “earnings manipulation happens as an instance where management violates Generally Accepted Accounting Principles (GAAP) in order to beneficially represent the firm’s financial performance.” In this research, the development of the Beneish model (DBM) was done through emphasizing non-accounting variables, including the Information Asymmetry (IS) and Product Market Competition (PMC). The data was collected for 184 companies listed in Tehran Stock Exchange (TSE) during the past 11 years 2006-2017. The predictive accuracy of research models by combination of Artificial Neural Network(ANN) and Imperialist Competition Algorithm (ICA) compared to Particle Swarm Optimization(PSO) in the detect and identification of earning manipulator companies after estimation. The area under curve(AUC) of Receiver Operating Characteristic (ROC) of Beneish Model (BM) and the research proposed model (DBM) by the combined neural network and ICA were estimated at 0.6001 and 0.6108, respectively, and by the combined neural network and PSO were estimated at 0.538 and 0.3355, respectively. The prediction accuracy of BM and DBM by the ANN-ICA is 57.55%, 63.86%, respectively and by the ANN-PSO algorithm are 55.71% and 59.84%, respectively. Also, the reduction rate of prediction error by ANN-ICA has increased from 3.77 % to 6.13%. The AUC of the ROC in the BM was in the fail testing range, and the ability of the BM to detect and identify earning manipulator companies was rejected. With the development of the model and the incorporation of environmental variables including IS and PMC to the BM (1999), this area has increased, passed the fail testing range and improved to poor test range, but is still a poor test result and the DBM does not fully distinguish between the two groups of earning manipulator and non-manipulator companies. Also, the predictive accuracy of the research models BM-DBM by the ANN-ICA has been improved in comparison to ANN-PSO.
 
Article number: 4
Keywords: Imperialist competition Algorithm, Product competition market, Artificial Neural Network, Beneish Model, Information environment
Full-Text [PDF 1196 kb]   (45 Downloads)    
Type of Study: Research | Subject: Special
Received: 2022/08/17 | Accepted: 2022/08/17 | Published: 2022/10/11
Add your comments about this article
Your username or Email:

CAPTCHA


XML   Persian Abstract   Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Comparison of the Prediction Accuracy of Earning Manipulation in Development of the Beneish Model by combination of Artificial Neural Network and Imperialist Competition and Particle Swarm Optimization Algorithms. 3 2022; 1 (2) :31-41
URL: http://ijamac.com/article-1-31-en.html


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 1, Issue 2 (6-2022) Back to browse issues page
مجله بین المللی مدیریت و حسابداری پیشرفته International Journal of Advanced Management and Accounting
Creative Commons License

All works in this site are licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Persian site map - English site map - Created in 0.05 seconds with 30 queries by YEKTAWEB 4533