Development of Earning Manipulation Prediction Model Applying Hybrid Neural Network and Cosmology Based Algorithms

اقتصاد پولی مالی

Article 3, Volume 28, Issue 21, November 2021, Pages 57-86   

Document Type: Original Article

DOI: 10.22067/mfe.2021.71593.1099

Authors

Nahid Maleki Nia¹; reza tehrani^{* 2}; Akbar Tabriz Akbar³; Mirfeiz Fallah shams⁴

¹Ph.D student of financial-Industrial management, Department of Industrial management, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran.

²Professor, Department of Finance, Faculty of Management, University of Tehran, Tehran, Iran.

³Professor, Department of Industrial Management, Management and Accounting Faculty, Shahid Beheshti University, Tehran, Iran.

⁴Associate professor, Department of Finance, Central Tehran branch, Islamic Azad University, Tehran, Iran.

Abstract

Extended abstract
1- INTRODUCTION
Accurately predicting earning manipulation in order to detect and identify manipulation of financial statements has always been one of the most fundamental challenges ahead of financial reports users. Because of increasing financial reporting fraud, this fact resulted in investor distrust of capital markets in recent years. The purpose of this study is to answer the questions whether it is possible to detect earning manipulation in financial statements based on the Beneish model? is it possible to detect earning manipulation in financial statements based on the proposed model? and does the proposed model predict better than the Beneish model in detecting earning manipulation? The findings of this research can be concidered by investors, creditors, auditors, regulators and other users to help them in making decisions and offering appropriate solutions. In order to detect earning manipulation and enhance the predictive accuracy of the earning manipulation model, it has been designed and presented a developed model based on Beneish model (1999). this study uses corporate governance variables i.e., audit committee structure, legal inspector and independent auditor, board of director's structure and corporate ownership structure requirements.
2- THEORETICAL FRAMEWORK
 Benish (1999) investigated 74 earning-manipulator companies applying probit analysis during 1982-1992. He assigned the number 1 to the manipulative companies and the number zero to the non-manipulative companies and calculated the coefficients of the independent variables. The cut-off point of this model was -1.78. Therefore, if the M-score  is greater than -1.78, it is likely that the company is earning manipulator. The overall accuracy of the model was confirmed at 76%.
By using eight accounting variables in its model, Beneish showed that the probability of earning manipulation increases with unusual increase in receivables, decrease in gross profit margin, decrease in asset quality, sales growth and increase in accruals. But what is hidden from view in this model, is the attention to the control of mechanism to reduce transaction and agency costs. Studies conducted to develop the Beneish model have also been based solely on accounting data and have ignored the implications of control mechanisms in model development. Therefore, in order to improve the predictive power of the beneish model, corporate governance system can be considered as a deterrent factor from earning manipulation.
3- METHODOLOGY
 The data of this study are drawn from the annual financial statements and reports of a sample of 81 non-financial listed companies on TSE over the period  2012-2018  i.e., 567 firm-year observations   and  analyzed by the hybrid multi-layer perceptron (MLP) neural network and cosmology based algorithms i.e.,  black-hole based optimization (BHBO), big bang-big crunch (BBBC) and galactic swarm optimization (GSO). It has been applied feed forward net to design the initial and final neural network model by structure of 8-17-1-1 for Beneish model (1999) and of 25-17-1-1 for the proposed model.This study also compares models based on hybrid neural networks and cosmological algorithms and the best and weakest cosmological algorithms are determined in neural network training to detect earning manipulation.
4- RESULTS & DISCUSSION
The numerical value of the area under the curve (AUC) of the receiver operating characteristic gives an idea about the detection power which it has been in the rejected range of 0.74 to 0.55 for the Beneish model (1999) and in the accepted range of 0.97 to 0.75 for the proposed model. The best cut-off points and the best accuracy of the Beneish model (1999) have been estimated up to 0.4014, 63.49%, respectively, by the hybrid multi-layer perceptron neural network and big bang-big crunch algorithm (MLP-BBBC). The best cut-off point and the best accuracy of the proposed model have been estimated up to 0.4023 and 87.30 percent, respectively, by the hybrid multi-layer perceptron neural network and galactic swarm optimization algorithm (MLP-GSO). The estimated accuracy of the model by the hybrid methods of multi-layer perceptron neural network and galactic swarm optimization algorithm (MLP-GSO), hybrid multi-layer perceptron neural network and big bang-big crunch algorithm (MLP-BBBC) and hybrid multi-layer perceptron neural network and black-hole based optimization algorithm (MLP-BHBO) has been increased from 59.08, 63.49 and 57.5 percentages to 87.3, 79.72 and 74.25 percentages, respectively.
5- CONCLUSIONS & SUGGESTIONS
This evidence indicates that predictive power of the model has been enhanced in detecting earning-manipulator companies and training error of the network has been decreased up to 12.7 percentages by hybrid method of multi-layer perceptron neural network and galactic swarm optimization algorithm (MLP-GSO). Therefore, it can be concluded that the integration of corporate governance variables as non-accounting variables to the Beneish model (1999) has been more effective in detecting and identifying earning manipulation. This evidence is consistent with this fact that a significant reduction in mean square error (MSE) is up to 23.81% and as a result the predictive power of proposed model has been significantly improved. The area under the curve of the black-hole based optimization (BHBO) and big bang-big crunch (BBBC) algorithms is covered by the galactic swarm optimization (GSO) algorithm in the proposed model. Also the area under the curve of the black-hole based optimization (BHBO) and galactic swarm optimization (GSO) algorithms is covered by the big bang-big crunch (BBBC) algorithm in Beneish model(1999). Therefore, the best algorithms for training the multi-layer perceptron neural network belong to the galactic swarm optimization (GSO) algorithm in the proposed model by the 12.7% error and to the Big Bang- Big Crunch (BB-BC) algorithm in Beneish model (1999) by the 36.51% error compared to the other cosmological algorithms in this study to detect and identify of manipulator companies.

Keywords

Multi-layer perceptron neural network; Cosmology algorithms; Beneish model; corporate governance system

Supplementary Files

Extended abstract 21.pdf

References

References

Abbaszade, M.; Hesarzade, R.; Jabbari Noghabi, M., & Arefi Asl, S. (2015). A Meta-analysis of corporate governance and earnings management. Accounting and Auditing Review, 22(1), 59-84.(in Persian)

Ahmadpour, A.; Tavakolnia, E., & Masoomi, T. (2015). Investigating the moderating effect of auditor industry specialization on the relationship between board governance and accruals based earnings management: Empirical evidence from companies listed in Tehran.  Journal of Management Accounting and Auditing Knowledge, 4,93-106.(in Persian)

Ansari, A.; Khorshidi  A., & Shirzad, A. (2014). The investigation effect of accruals-based earnings management and real earnings management on stock liquidity and firm value.  Journal of Management Accounting and Auditing Knowledge, 3,41-54.(in Persian)

Asgari Alouj, H.; Nikbakht, M.; Karami, G., & Momeni, M. (2020). Development of the Beneish model by combining artificial neural network and particle swarm optimization algorithm for earnings management prediction.  Accounting and Auditing Review, 26(4), 615-638.(in Persian)

Asghar, A. ; Sajjad, S. ; Shahzad, A.  ,& Matemilola, B. T.  (2020), "Role of discretionary earning management in corporate governance-value and corporate governance-risk relationships",  Corporate Governance, 20(4), 561-581.

Bani Mahd, B. ; Moradzadeh Fard, M ,& Morvarid Araqi, Fatemeh (2014). Positive change of earnings per share and share price: functional fixation hypothesis. Management Accounting, 7(1), 67-77.(in Persian)

Beneish, M. D. (1999). The detection of earnings manipulation.  Financial Analysts Journal,  55(5), 24-36.

Bilan, Y. ,& Jurickova, V. (2021). Detection of earnings management by different models. in SHS Web of Conferences , 92, EDP Sciences.

Bouchekara, H. R. (2013). Optimal design of electromagnetic devices using a black-hole-based optimization technique.  IEEE transactions on magnetics,  49(12), 5709-5714.

Britannica, E. (2010). Encyclopædia Britannica ultimate reference suite.  Chicago: Encyclopædia Britannica.

Erol, O. K., & Eksin, I. (2006). A new optimization method: big bang–big crunch.  Advances in Engineering Software,  37(2), 106-111.

Ghorbani, B.; Hosseini Ghoncheh, S. J ,& Mohammadilr, Z. (2018). The Impact of disclosure of non-Financial strategic information on profit management. Financial Accounting and Auditing Research, 9(35), 23-40.(in Persian)

Hatamlou, A. (2013). Black hole: A new heuristic optimization approach for data clustering.  Information Sciences,  222,175-184.

Javady Nia, A. (2020). The impact of managerial ability on the relationship between political connections and representation agency costs in companies listed in Tehran Stock Exchange.  Journal of Accounting and Management Vision, 3(21), 144-163.(in Persian)

Kao, L.; Chen, A. ,& Lu, C. S. (2018). Ex ante and ex post overvalued equities: The roles of corporate governance and product market competition.  Asia Pacific Management Review, 23(3), 209-221.

Kaveh, A., & Bakhshpoori, T. (2019). Big bang-big crunch algorithm. In metaheuristics: Outlines, MATLAB Codes and Examples , 31-40,Springer, Cham.

Khodabande, A. ,& Rezaie, F. (2019). Managing the impact of information on corporate financial reporting. Journal of New Research Approaches in Management and Accounting, 2(8), 1-14.(in Persian)

Kordestani, G. ,& Tatli, R. (2016). The prediction of earnings manipulation: development of a model.  Accounting and Auditing Review, 23(1), 73-96.(in Persian)

Kukreja, G.; Gupta, S. M.; Sarea, A. M.  ,& Kumaraswamy, S.  (2020), Beneish M-score and Altman Z-score as a catalyst for corporate fraud detection,  Journal of Investment Compliance, 21(4), 231-241.

Moghaddam, A. ,& Ghadrdan, E. (2019). Investigating the factors affecting unmanaged profit by management.  Accounting and Auditing Studies, 8(31), 59-74.(in Persian)

Muthiah-Nakarajan, V., & Noel, M. M. (2016). Galactic swarm optimization: A new global optimization metaheuristic inspired by galactic motion.  Applied Soft Computing,  38,771-787.

Nakhaei, H., & Ahmadpour, J. (2020). The effect of the structure of the board of directors and the corporate governance on the performance and unconditional standards of performance of Iranian companies.  Journal of Accounting and Management Vision, 3(22), 82-101.(in Persian)

Pour-Ali, M R.,& Kouchaki Tajani, M. (2020). Comparing the accuracy of companies' profit manipulation prediction using colonial competition algorithm and genetic algorithm. The First International Conference on New Challenges and Solutions in Industrial Engineering, Management and Accounting. (in Persian)

Qaemi, F.; Moradi, Z. ,& Alavi, G. H. (2021). The effect of audit committee characteristics on internal controls and earnings management. Financial Accounting and Auditing Research, 46, 259 - 280.(in Persian)

Rahimian, N., & hajiheydari, R. (2019). Fraudulent financial statement detection using: Adjusted-M-score-Beneish models and financial ratios. . Empirical Research in Accounting, 9(1), 47-70.(in Persian)

Razali, W. A. A. W. M., & Arshad, R. (2014). Disclosure of corporate governance structure and the likelihood of fraudulent financial reporting.  Procedia-Social and Behavioral Sciences,  145, 243-253.

Repousis, S. (2016). Using Beneish model to detect corporate financial statement fraud in Greece.  Journal of Financial Crime, 23(4), 1063-1073.

Salehi-Kordabadi, S., & Zad-Dousti, F. (2020). The relationship between corporate governance, earnings management and financial performance in companies listed on the Tehran Stock Exchange.  Journal of Accounting and Management Vision, 3(26), 92-109.(in Persian)

Serrano-Cinca, C.; Gutiérrez-Nieto, B., & Bernate-Valbuena, M. (2019). The use of accounting anomalies indicators to predict business failure.  European Management Journal,  37(3), 353-375.

Shakouri, M. M.; Taherabadi, A.; Ghanbari, M., & Jamshidinavid, B. (2021). Explaining the Beneish model and providing a comprehensive model of fraudulent financial reporting (FFR).  International Journal of Nonlinear Analysis and Applications,  12,39-48.(in Persian)

Sheari Anaghiz, S.; Rahimian, N. A.; Salehi Ghadyani, J., & Khorasani, A. (2017). Investigating and applying the accuracy of the results obtained from "Beneish" and "Modified Beneish" models based on Iran's economic environment in detecting and exposing fraudulent financial reporting.  Financial Management Perspective, 7(18), 105-124.(in Persian)

Suryanto, T., & Grima, S. (2018). The Corporate decision in Indonesia: a result of corporate governance requirements, earning management and audit reports. In Governance and Regulations’ Contemporary Issues. Emerald Publishing Limited, 183-206.

Tazikeh Lamski, A., & Saeedi, P. (2020). Investigate how cheating triangles are formed by managers to make more profit from stakeholders. Economic Studies, Financial Management and Accounting, 5(1), 189-200.(in Persian)

Valizadeh Larijani, A.; Rahmani, A., & Sadeh, S. (2018). Internal control report disclosure, agency cost and earnings management internal control report disclosure, agency cost and earnings management.  Journal of Management Accounting and Auditing Knowledge, 7(25), 29-40.(in Persian)

Watts, R., & Zimmerman, J. (1990). Positive accounting theory. Prentice Hall Eaglewood Cliffts.

Wyrobek, J. (2020). Application of machine learning models and artificial intelligence to analyze annual financial statements to identify companies with unfair corporate culture.  Procedia Computer Science,  176, 3037-3046.