Development of the Beneish Model by Combining Artificial Neural Network and Particle Swarm Optimization Algorithm for Earnings Management Prediction

Document Type : Research Paper


1 Department of Accounting, Islamic Azad University, beleh savar branch

2 Associate Prof., Department of Accounting, Faculty of Management, Tehran University, Tehran, Iran.

3 Prof., Department of Industrial Management, Faculty of Management, Tehran University, Tehran, Iran.


Objective: According to Beneish (1999), “earnings manipulation happens as an instance where management violates Generally Accepted Accounting Principles (GAAP)inordertobeneficiallyrepresentthefirm’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).
Methods: The data was collected for 184 companies listed in the Tehran Stock Exchange (TSE) during the past 11 years 2006-2017. The coefficients of models were estimated by trained Artificial Neural Network (ANN) through PSO algorithm. In order to provide the potential of comparability, ten run with 300 iterations in each run were done for both the Beneish model (BM) and (DBM), then were stopped after convergence.
Results: Research results indicate that training error of ANN trained by PSO algorithm measured by mean square error (MSE) was reduced from 0/0807 to 0/0777 by the development of BM. The area under Receiver Operating Characteristic (ROC) for BM was calculated up to 0/5792, which is located in very low confidence range of 0/5-0/6, indicating failed test result and high prediction error up to 39/74 percent. Consequently the best cut-off point and the best precision for BM were estimated to be 0/5021, 60/26 percent, by the maximum accuracy method, respectively. Furthermore, the results show that the AUC for DBM was increased to 0/6335 through incorporating environmental variables of Product Market Competition (PMC) and information symmetry (IS) to the BM, which is still out of an acceptable range of 0/7–0/8 for a relatively good test, indicating poor test result and high model prediction error up to 32/58 percent. Consequently the best cut-off point and the best precision for DBM were estimated to be 0/5304, 67/42 percent by the intersection point of minimum distance and Youden's index, respectively. Incorporating PMC and IS variables to the original model of Beneish decreased model prediction error from 39/74 to 32/58 percent, which is not statistically significant. Nevertheless, this fact improved the predictive power of the BM slightly insignificant.
Conclusion: The findings indicate that the BM is a random model in Iranian capital market and impotent to detect two groups of earning manipulator and non-earning manipulator companies. Although findings indicate that the DBM is a little bit more powerful than the BM and confirm that the impact of environmental variables of PMC and IS is slightly insignificant, indicating the test outcome is still weak and the DBM is an approximately random model in identifying two groups of earning manipulator and non-earning manipulator companies.


Ajina, A., Habib, A. (2017). Examining the relationship between Earning management and market liquidity. Research in International Business and Finance, 42, 1164-1172.
Bahri Sales, J., Pak Maram, A. & Qaderi, G. (2018). Explanation of the relationship between product market competition and corporate earnings management (Evidence from discretionary Accruals items). Quarterly journal of Management Accounting, 11 (38), 15-26. (in Persian)
Barton, J., Hansen, T., & Pownall, G. (2010). Which performance measures do investors around the world value the most—and why? The Accounting Review, 85, 753–789.
Barzegar, G., Taleb Tabar Ahangar, M. & Esabat Tabari, E. (2014). Investigating of the Relationship between Product Market Competition and Earnings Management (Case Study: Companies Listed in Tehran Stock Exchange). Quarterly Journal of Financial Accounting Research, 6 (4), 88-73. (in Persian)
Beneish, M. D. (1999). The Detection of Earnings Manipulation. Financial Analysts Journal, 55 (5), 24-36.
Cormier, D., Sylvain, H. & Marie, L. (2013). The incidence of earnings management on information asymmetry in a certain environment: Some Canadian evidence. Journal of International Accounting, Auditing and Taxation, 22, 26– 38.
Derrac, J., García, S., Molina, D. & Herrera, F. (2011). A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm and Evolutionary Computation, 1(1), 3-18.
Dhaliwal, D., Huang, S., Khurana, I. K., & Pereira, R. (2008). Product market competition and accounting conservatism. Review of Accounting Studies, 19, 1309–1345.
Healy, P. (1985). The effect of bonus schemes on accounting decisions. Journal of Accounting and Economics, 7, 85-107.
Heidarzadeh Hanzaei, A., Barati, L. (2019). Information Environment and Earnings Management in Companies to Dual Holdings. Journal of Investment Knowledge, 8(29), 315-332. (in Persian)
Jones, J.J. (1991). Earnings Management during Import Relief Investigations. Journal of Accounting Research, 29(2), 193-228.
Kordestani, G. & Tatli, R. (2014). Identification the Efficient and Opportunistic Earnings Management Approaches in the Earnings Quality Levels. Accounting and Auditing Review, 21(3), 293–312. (in Persian)
Laksmana, I., Yang, Y. W. (2014). Product market competition and earnings management: Evidence from discretionary accruals and real activity manipulation. Advances in Accounting, 30(2), 263-275.
 Lazzem, S., Jilani, F. (2018). The impact of leverage on accrual-based earnings management: The case of listed French firms. Research in International Business and Finance, 44, 350-358.
Li, T., & Zaiats, N. (2017). Information environment and earnings management of dual class firms around the world. Journal of Banking & Finance, 74, 1-23.
Mashayekh, S., Arbabi, Z., Rahimi Far, M. (2013). Study of Earnings Management Incentives. Journal of Accounting Research, 3(2), 53-70. (in Persian)
Mirjalili, S., Mirjalili, S. M. & Lewis, A. (2014). Let a biogeography-based optimizer train your Multi-Layer Perceptron. Information Sciences, 269, 188–209.
Moradi, M. (2015). Designing Earnings Quality Model in Tehran Stock Exchange (TSE) with Emphasizing on the Role of Accruals. Journal of Accounting and Auditing Research, 25, 76-99. (in Persian)
Moradi, M., Osoolian, M., Norouzi, M. (2014). Audit Opinion and Earnings Management: Uncertainty in Going-concern. Accounting and Auditing Review, 21(3), 313-328. 
(in Persian)
Najafizadeh, B. & Kayhan, M. (2016). Investigating of the Relationship between Earnings Management and Information Asymmetry in Environmental Uncertainty in Companies Listed in Tehran Stock Exchange (TSE), 4th National Conference on Management, Economics and Accounting, Tabriz, Industrial Management Organization of East Azarbaijan, University of Tabriz. (in Persian)
Namazi, M., Rezaei, G., Momtazian, A. (2015). Product Market Competition and Accounting Information Quality. Journal of accounting advances, 6(2), 131-166. (in Persian)
Piri, P., Gorbani, M. (2018). Evaluation the Relationship between the Type of Independent Auditor's Opinion and Earnings Quality. Accounting and Auditing Review, 24(4), 483-502. (in Persian)
Rahmani, A., Ghashghaei, F. (2018). The Relation between Accounting Comparability and Earning Management, Accounting and Auditing Review, 24(4), 527-550. (in Persian)
Rahul, K., Seth, N., Dinesh Kumar, U. (2018). Spotting Earnings Manipulation: Using Machine Learning for Financial Fraud Detection. In: Bramer M., Petridis M. (Eds) Artificial Intelligence XXXV. SGAI. Lecture Notes in Computer Science, Springer, 343-356.
Ramírez Orellana, A., Martínez Romero, M. J. & Mariño Garrido, T. (2017). Measuring fraud and earnings management by a case of study: Evidence from an international family business. European Journal of Family Business, 7(1-2), 41-53.
Rostami, W., Ghorbani, B. & Tadrisi, M. (2015). The Impact of Product Market Competition on Real Profit Management of Companies Listed in Tehran Stock Exchange (TSE). First International Conference on Management and Accounting with Value Creation Approach, Islamic Azad University of Fars, Shiraz. (in Persian)
Rotemberg, J. & Scharfstein, D. (1990). Shareholder value maximization and produc market competition. Review of Financial Studies, 3(3), 367–391.
Salehi, M. & Farokhi Pile Rood, L. (2018). Predicting of Earnings Management Using Neural Network and Decision Tree. Quarterly Journal of Financial Accounting and Auditing Research, 10 (37), 1-24. (in Persian)
Setayesh, M., Mohammadian, M., Mehtari, Z. (2015). Extended Abstract Investigation of Interactive Effect Accounting Information Quality and Information Asymmetry on Inefficient Investment Tehran Stock Exchange (TSE). Journal of accounting advances, 7(1), 73-102. (in Persian)
Sheri Anagiz, S., Rahimiyan, N., Salehi Sedghiyani, J. & Khorasani, A. (2017). Investigating and Adjusting the Accuracy of the Results of Beneish and Modified Beneish Models Based on Iran's Economic Environment in Discovering and Disclosure of Fraudulent Financial Reporting. Quarterly Journal of Financial Management Outlook, 7 (18), 105-123. (in Persian)
Sttar, A., & Wdaa, I. (2008). Differential evolution for neural networks learning enhancement, Masters Thesis, Universiti Teknologi Malaysia.
Taherverdi, M. (2014). The Impact of Corporate Governance and Earnings Management on Earnings Quality. Islamic Azad University, Central Tehran Branch. (in Persian)
Tarjoa, N. H. (2015).Application of Beneish M-Score Models and Data Mining to Detect Financial Fraud. Social and Behavioral Sciences, 211, 924 – 930.
Watts, R. & Zimmerman, J. (1986).  Positive Accounting Theory. prentice-Hall, Englewood Cliffs, New Jersy.