Predicting Audit Opinion in Consolidated Financial Statements with Artificial Neural Networks
Abstract
:1. Introduction
2. Literature Review
2.1. Audit Opinion Prediction Models
2.2. Characteristics of Consolidated Financial Statements
3. Sample and Variables
3.1. Sample
3.2. Variables
4. Model Research Design
5. Results
5.1. Exploratory Analysis
5.2. Model Evaluation
5.3. Sensitivity Analysis
6. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Gaganis, C.; Pasiouras, F.; Doumpos, M. Probabilistic neural networks for the identification of qualified audit opinions. Expert Syst. Appl. 2007, 32, 114–124. [Google Scholar] [CrossRef]
- Fernández-Gámez, M.A.; García-Lagos, F.; Sánchez-Serrano, J.R. Integrating corporate governance and financial variables for the identification of qualified audit opinions with neural networks. Neural Comput. Appl. 2016, 27, 1427–1444. [Google Scholar] [CrossRef]
- Darrough, N.; Harris, T. Do Management Forecasts of Earnings Affect Stock Prices in Japan? In Japanese Financial Market Research; North-Holland: Amsterdam, the Netherlands, 1991; pp. 197–229. [Google Scholar]
- Harris, T.S.; Lang, M.; Moller, H.P. The Value Relevance of German Accounting Measures: An Empirical Analysis. J. Account. Res. 1994, 32, 187–209. [Google Scholar] [CrossRef]
- Niskanen, J.; Kinnunen, J.; Kasanen, E. A note on the information content of parent company versus consolidated earnings in Finland. Eur. Account. Rev. 1998, 7, 31–40. [Google Scholar] [CrossRef]
- Abad, C.; Laffarga, J.; García-Borbolla, A.; Larrán, M.; Piñero, J.M.; Garrod, N. An evaluation of the value relevance of consolidated versus unconsolidated accounting information: Evidence from quoted Spanish firms. J. Int. Financ. Manag. Account. 2000, 11, 156–177. [Google Scholar] [CrossRef]
- Chow, D.; Humphrey, C.; Moll, J. Developing whole of government accounting in the UK: Grand claims, practical complexities and a suggested future research agenda. Financ. Account. Manag. 2007, 23, 27–54. [Google Scholar] [CrossRef]
- Sotti, F. The value relevance of consolidated & separate financial statements: Are non-controlling interests relevant? Afr. J. Bus. Manag. 2018, 12, 329–333. [Google Scholar]
- Goncharov, I.; Werner, J.R.; Zimmermann, J. Legislative demands and economic realities: Company and group accounts compared. Int. J. Account. 2009, 44, 334–362. [Google Scholar] [CrossRef]
- Pourheydari, O.; Nezamabadi-pour, H.; Aazami, Z. Identifying qualified audit opinions by artificial neural networks. Afr. J. Bussines Manag. 2012, 6, 11077–11087. [Google Scholar]
- DeAngelo, L. Auditor size and audit quality. J. Account. Econ. 1981, 3, 183–199. [Google Scholar] [CrossRef]
- Mansi, S.A.; Maxwell, W.F.; Miller, D.P. Does auditor quality and tenure matter to investors? Evidence for bond market. J. Account. Res. 2004, 42, 755–793. [Google Scholar] [CrossRef]
- Levitan, A.S.; Knobblet, J.A. Indicators of exceptions to the going-concern assumption. Audit. A J. Pract. Theory 1985, 5, 26–39. [Google Scholar]
- Lennox, C. Do companies successfully engage in opinion-shopping? Evidence from the UK. J. Account. Econ. 2000, 29, 321–337. [Google Scholar] [CrossRef]
- Moalla, H. Audit report qualification/modification: Impact of financial variables in Tunisia. J. Account. Emerg. Econ. 2017, 7, 468–485. [Google Scholar] [CrossRef]
- Spathis, C. Detecting false financial statements using published data: Some evidence from Greece. Manag. Audit. J. 2002, 17, 179–191. [Google Scholar] [CrossRef] [Green Version]
- Spathis, C.; Doumpos, M.; Zopounidis, C. Using client performance measures to identify pre-engagement factors associated with qualified audit reports in Greece. Int. J. Account. 2003, 38, 267–284. [Google Scholar] [CrossRef]
- Pasiouras, F.; Gaganis, C.; Zopounidis, C. Multicriteria decision support methodologies for auditing decisions: The case of qualified audit report in the UK. Eur. J. Oper. Res. 2007, 180, 1317–1330. [Google Scholar] [CrossRef]
- Doumpos, M.; Gaganis, C.; Pasiouras, F. Explaining qualifications in audit reports using a support vector machine methodology. Intell. Syst. Acc. Financ. Manag. 2005, 13, 197–215. [Google Scholar] [CrossRef]
- Kirkos, E.; Spathis, C.; Nanopolulos, A.; Manolopoulos, Y. Identifying Qualified Auditors´Opinions: A Data Mining Approach. J. Emerg. Technol. Account. 2007, 4, 183–197. [Google Scholar] [CrossRef]
- Laitinen, E.K.; Laitinen, T. Qualified audit reports in Finland: Evidence from large companies. Eur. Account. Rev. 1998, 7, 639–653. [Google Scholar] [CrossRef]
- Gaganis, C.; Pasiouras, F. A multivariate analysis of the determinants of auditors’ opinions on Asian Banks. Manag. Audit. J. 2007, 22, 268–287. [Google Scholar] [CrossRef]
- Gaganis, C.; Pasiouras, F.; Tanna, S.; Zopounidis, C. Binary Choice Models for External Auditors Decisions in Asian Banks. Oper. Res. Int. J. 2008, 8, 123–139. [Google Scholar] [CrossRef] [Green Version]
- Ebrahimi, F.; Sarikhani, M.; Mojtaba, S. Finding rules for audit opinions prediction through data mining methods. Eur. Online J. Nat. Soc. Sci. 2012, 1, 28–36. [Google Scholar]
- Yasar, A.; Yakut, E.; Gutnu, M. Predicting Qualified Audit Opinions Using Financial Ratios: Evidence from the Istanbul Stock Exchange. Int. J. Bus. Soc. Sci. 2015, 8, 57–67. [Google Scholar]
- Heald, D.; Georgiou, G. Consolidation principles and practices for the UK government sector. Account. Bus. Res. 2000, 30, 153–167. [Google Scholar] [CrossRef]
- Choi, F.D.S.; Mueller, G.G. International Accounting; Prentice-Hall: Upper Saddle River, NJ, USA, 1992. [Google Scholar]
- Delvaille, P.; Ebbers, G.; Saccon, C. International Financial Reporting Convergence: Evidence from Three Continental European Countries. Account. Eur. 2005, 2, 137–164. [Google Scholar] [CrossRef]
- Lamb, M.; Nobes, C.; Roberts, A. International Variations in the Connection Between Tax and Financial Reporting. Account. Bus. Res. 1998, 28, 173–188. [Google Scholar] [CrossRef]
- Macías, M.; Muiño, F. Examining dual accounting systems in Europe. Int. J. Account. 2011, 46, 51–78. [Google Scholar] [CrossRef] [Green Version]
- Nobes, C. Towards a general model of the reasons for international differences in financial reporting. Abacus 1998, 34, 162–187. [Google Scholar] [CrossRef]
- Oliveras, E.; Puig, X. The Changing Relationship between Tax and Financial Reporting in Spain: EBSCOhost. Account. Eur. 2005, 2, 195–207. [Google Scholar] [CrossRef]
- Bartov, E.; Goldberg, S.; Kim, M. Comparative Value Relevance Among German, U.S., and International Accounting Standards: A German Stock Market Perspective. J. Account. Audit. Financ. 2005, 20, 95–119. [Google Scholar] [CrossRef]
- Jermakowicz, E.; Prather-Kinsey, J.; Wulf, I. The Value Relevance of Accounting Income Reported by DAX-30 German Companies. J. Int. Financ. Manag. Account. 2007, 18, 151–191. [Google Scholar] [CrossRef]
- Barth, M.E.; Landsman, W.R.; Lang, M.H. International Accounting Standards and Accounting Quality. J. Account. Res. 2008, 46, 467–498. [Google Scholar] [CrossRef] [Green Version]
- Paananen, M.; Lin, C. The development of accounting quality of IAS and IFRS over time: The case of Germany. J. Int. Account. Res. 2009, 8, 1–41. [Google Scholar] [CrossRef] [Green Version]
- Vuko, T.; Cular, M. Finding determinants of audit delay by pooled OLS regression analysis. Croat. Oper. Res. Rev. 2014, 81, 81–91. [Google Scholar] [CrossRef] [Green Version]
- Klein, A. Audit committee, board of director characteristics, and earnings management. J. Acc. Econ. 2002, 33, 375–400. [Google Scholar] [CrossRef] [Green Version]
- Peasnell, K.V.; Pope, P.F.; Young, S. Board monitoring and earnings management: Do outside directors influence abnormal accruals? J. Bus. Financ. Acc. 2005, 32, 1311–1346. [Google Scholar] [CrossRef]
- Nuñez de Castro, L.; von Zuben, F.J. Optimised training techniques for feedforward neural networks. In Technical Report DCA RT 03/98; Department of Computer Engineering and Industrial Automation. FEE/UNICAMP: São Paulo, Brasil, 1998. [Google Scholar]
- Zahedi, F. A meta-analysis of financial application of neural networks. Int. J. Comput. Intell. Organ. 1996, 1, 164–178. [Google Scholar]
- Müller, V.O. The impact of IFRS adoption on the quality of consolidated financial reporting. 2nd World Conference On Business, Economics and Management—WCBEM 2013. Procedia Soc. Behav. Sci. 2014, 109, 976–998. [Google Scholar]
- Srivastava, N.; Hinton, G.; Krizhevsky, A.; Sutskever, I.; Salakhutdinov, R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 2014, 15, 1929–1958. [Google Scholar]
- Cawley, G.C.; Talbot, N.L.C. On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation. J. Mach. Learn. Res. 2010, 11, 2079–2107. [Google Scholar]
- Duchi, J.; Hazan, E.; Singer, Y. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. J. Mach. Learn. Res. 2011, 12, 2121–2159. [Google Scholar]
- Seising, R. The Emergence of Fuzzy Sets in the Decade of the Perceptron—Lotfi, A. Zadeh’s and Frank Rosenblatt’s Research Work on Pattern Classification. Mathematics 2018, 6, 110. [Google Scholar] [CrossRef] [Green Version]
- Jiang, P.; Hu, Y.-C.; Wang, W.; Jiang, H.; Wu, G. Interval Grey Prediction Models with Forecast Combination for Energy Demand Forecasting. Mathematics 2020, 8, 960. [Google Scholar] [CrossRef]
- Hinton, G. Neural Networks for Machine Learning—Lecture 6a—Overview of Mini-Batch Gradient Descent. 2012. Available online: http://www.cs.toronto.edu/~hinton/coursera/lecture6/lec6.pdf (accessed on 28 March 2020).
- Kingma, D.P.; Ba, J.L. Adam: A Method for Stochastic Optimization. In Proceedings of the International Conference on Learning Representations, San Diego, CA, USA, 7–9 May 2015. [Google Scholar]
- Zeiler, M.D. ADADELTA: An Adaptive Learning Rate Method. Available online: http://arxiv.org/abs/1212.5701 (accessed on 28 March 2020).
- Dozat, T. Incorporating Nesterov Momentum into Adam. In Proceedings of the ICLR Workshop, (1), 2013–2016, San Juan, Puerto Rico, 2–4 May 2016. [Google Scholar]
- Reddi, S.J.; Kale SKumar, S. On the Convergence of Adam and Beyond. In Proceedings of the International Conference on Learning Representations, Vancouver, Canada, 30 April–30 May 2018. [Google Scholar]
- Loebbecke, J.K.; Eining, M.M.; Willingham, J.J. Auditor’s experience with material irregularities: Frequency, nature, and detectability. Audit. A J. Pract. Theory 1989, 9, 1–28. [Google Scholar]
- Summers, S.L.; Sweeney, J.T. Fraudulently misstated financial statements and insider trading: An empirical analysis. Account. Rev. 1998, 73, 131–146. [Google Scholar]
- Beasley, M.; Carcello, J.; Hermanson, D. Fraudulent Financial Reporting (1987–1997). An. Analysis of US Public Companies; Committee of Sponsoring Organizations of the Treadway Commission: New York, NY, USA, 1999. [Google Scholar]
- Hashem, S. Sensitivity analysis for feedforward artificial neural networks with differentiable activation functions. Int. Jt. Conf. Neural Netw. 1992, 419–424. [Google Scholar] [CrossRef]
- Lisbon, P.; Mehridehnavi, A.; Martin, P. The interpretation of supervised neural networks. Proc. Workshop Neural Netw. Appl. Tools 1994, 11–17. [Google Scholar] [CrossRef]
- Ribeiro, M.T.; Singh, S.; Guestrin, C. Model-Agnostic Interpretability of Machine Learning. In Proceedings of the ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), New York, NY, USA, 23 June 2016. [Google Scholar]
- Gujarati, N.D. Basic Econometrics, 3rd ed.; McGraw-Hill: New York, NY, USA, 1995. [Google Scholar]
Industry Code | Description | Number of Groups |
---|---|---|
0 | Agriculture | 5 |
10 | Food industry | 11 |
11 | Manufacture of drinks | 3 |
12 | Tobacco | 6 |
13 | Textile industry | 9 |
14 | Clothes manufacturing | 10 |
16 | Wood and cork industry | 1 |
17 | Paper industry | 6 |
18 | Graphic arts | 3 |
2 | Chemical industry | 2 |
3 | Manufacture of transport equipment | 72 |
4 | Building construction | 6 |
5 | Air and maritime transport | 4 |
6 | Telecommunications | 47 |
7 | Architecture and engineering activities | 92 |
8 | Security and research activities | 13 |
9 | Creative, arts and entertainment activities | 9 |
Variables | Description |
---|---|
Financial parameters | |
ROA | Return on assets (%) |
ROE | Return on equity (%) |
Working capital | 103 € |
Working capital per employee | 103 € |
Sales per employee | 103 € |
Average cost per employee | 103 € |
Profit per employee | 103 € |
Operating income per employee | 103 € |
Total assets per employee | 103 € |
Current ratio | % |
Liquidity ratio | % |
EBITDA 1/Liabilities | EBITDA/Total liabilities |
Solvency ratio 1 | Profit of loss for the year + amortization/Current liabilities |
Solvency ratio 2 | Profit of loss for the year + amortization/Current liabilities—creditors |
EBIT margin | EBIT/Sales |
Profit margin | Profit/Sales |
Debtors’ collection period | Number of days |
Creditors’ payment period | Number of days |
Asset turnover | Total asset/Sales |
Fixed asset turnover | Fixed asset/Sales |
Salaries/Sales | 103 € |
EBITDA /Sales | 103 € |
Cash flow | 103 € |
Operating cash flow | 103 € |
Investment cash flow | 103 € |
Sales variation rate | % |
Results before tax variation rate | % |
Results variation rate | % |
Total assets | Log (total assets 103 €) |
Number of employees | Log (number of employees) |
Group size | Number of companies in the corporate group |
Non-financialparameters | |
Board members | Number of board members |
Qualitativeparameters | |
Auditor code | 1 = “Big 4”; 0 = Others |
Audit fees | Log (audit fees 103 €) |
Industry | Industry classification (CNAE-09) |
N | Mean | Median | S.D. | |||||
---|---|---|---|---|---|---|---|---|
UQ | Q 1 | UQ | Q | UQ | Q | UQ | Q | |
Group size | 203 | 86 | 98.64 | 54.5 | 10 | 11.5 | 338.99 | 133.33 |
Audit fees | 211 | 87 | 10.83 | 10.65 | 10.58 | 10.59 | 1.342 | 1.1 |
Board members | 211 | 87 | 9.54 | 7.05 | 7 | 6 | 9.54 | 5.96 |
Number of employees | 211 | 87 | 5.9 | 5.88 | 5.64 | 6.01 | 1.75 | 1.17 |
Log total assets | 211 | 87 | 18.53 | 18.3 | 18.22 | 18.16 | 1.57 | 1.12 |
Total assets per employee | 211 | 87 | 2241.03 | 1334.25 | 286.35 | 218.47 | 12,451.03 | 6488.92 |
Working capital | 211 | 87 | 75,598.06 | 34,535.31 | 21,385.85 | 18,334.31 | 264,536.07 | 56,773.34 |
Working capital per employee | 211 | 87 | 245.35 | 112.29 | 66.58 | 55.31 | 872.3 | 512.81 |
Sales per employee | 211 | 87 | 785.67 | 892.85 | 277.2 | 246.58 | 2820.41 | 3964.05 |
Average cost per employee | 211 | 87 | 40.21 | 92.23 | 37.32 | 38.87 | 19.36 | 471.32 |
Profit per employee | 211 | 87 | 42.57 | 63.08 | 6.27 | 9.66 | 193.73 | 255.87 |
Operating income per employee | 211 | 87 | 806.12 | 901.21 | 277.22 | 259.47 | 2872.58 | 3981.25 |
Economic profitability | 211 | 87 | 2.71 | 6.89 | 2.39 | 4.66 | 1.84 | 6.44 |
Financial profitability | 211 | 87 | 13.34 | 17.19 | 7.94 | 11.67 | 33.47 | 18.21 |
Current ratio | 211 | 87 | 1.07 | 4.33 | 0.95 | 1.05 | 1.45 | 27.14 |
Liquidity ratio | 211 | 87 | 2.3 | 5.4 | 0.96 | 1.2 | 5.24 | 29.04 |
EBITDA/Total liability | 211 | 87 | 0.05 | 0.1 | 0.05 | 0.08 | 0.02 | 0.078 |
Solvency ratio 1 | 211 | 87 | 0.06 | 0.25 | 0.06 | 0.15 | 0.02 | 0.42 |
Solvency ratio 2 | 211 | 87 | 0.22 | 0.68 | 0.15 | 0.42 | 0.239 | 1.39 |
EBIT margin | 211 | 87 | 7.17 | 7.84 | 3.24 | 6.06 | 12.66 | 12.4 |
Profit margin | 211 | 87 | 4.54 | 7.38 | 2.49 | 5.57 | 7.96 | 8.05 |
Debtors’ collection period | 211 | 87 | 102.72 | 82.57 | 85.84 | 80.22 | 109.85 | 50.16 |
Creditors’ payment period | 211 | 87 | 56.23 | 43.7 | 45.1 | 41.32 | 46.02 | 30.68 |
Asset turnover | 211 | 87 | 0.01 | 0.05 | 0.01 | 0.03 | 0.014 | 0.04 |
Fixed asset turnover | 211 | 87 | 0.29 | 1.84 | 0.04 | 0.1 | 2.63 | 15.55 |
Salaries/Sales | 211 | 87 | 0.19 | 0.21 | 0.14 | 0.17 | 0.19 | 0.16 |
EBITDA/Sales | 211 | 87 | 0.1 | 0.12 | 0.05 | 0.09 | 0.17 | 0.12 |
Cash flow | 211 | 87 | 38,603.45 | 13,436.96 | 3292.74 | 5729.42 | 214,364.83 | 22,865.52 |
Operating cash flow | 211 | 87 | 3.04 | −0.7 | 0.42 | 0.15 | 31.85 | 27.7 |
Investment cash flow | 211 | 87 | −2.86 | −5.9 | −0.06 | −0.15 | 9.79 | 32.76 |
Sales variation rate | 211 | 87 | 14.42 | 9.36 | 8.11 | 8.69 | 46.33 | 15.12 |
Results before tax variation rate | 211 | 87 | 43.71 | 63.63 | 6.16 | 3.12 | 156.03 | 268.55 |
Results variation rate | 211 | 87 | 55.92 | 323.8 | 0.02 | 8.79 | 364.98 | 2187.42 |
Training | Validation | Testing | ||||
---|---|---|---|---|---|---|
Mean | S.D. | Mean | S.D. | Mean | S.D. | |
Overall accuracy (%) | 0.865 | 0.015 | 0.825 | 0.043 | 0.825 | 0.042 |
F-measure | 0.864 | 0.014 | 0.824 | 0.042 | 0.824 | 0.041 |
Precision | 0.892 | 0.016 | 0.850 | 0.044 | 0.850 | 0.042 |
Sensitivity | 0.839 | 0.014 | 0.800 | 0.041 | 0.800 | 0.040 |
Specificity | 0.891 | 0.015 | 0.851 | 0.044 | 0.851 | 0.042 |
Variable | Tolerance | VIF |
---|---|---|
Industry | 0.980 | 1.020 |
Group size | 0.788 | 1.268 |
Auditor code | 0.638 | 1.567 |
Audit fees | 0.508 | 1.967 |
Board members | 0.775 | 1.291 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Sánchez-Serrano, J.R.; Alaminos, D.; García-Lagos, F.; Callejón-Gil, A.M. Predicting Audit Opinion in Consolidated Financial Statements with Artificial Neural Networks. Mathematics 2020, 8, 1288. https://doi.org/10.3390/math8081288
Sánchez-Serrano JR, Alaminos D, García-Lagos F, Callejón-Gil AM. Predicting Audit Opinion in Consolidated Financial Statements with Artificial Neural Networks. Mathematics. 2020; 8(8):1288. https://doi.org/10.3390/math8081288
Chicago/Turabian StyleSánchez-Serrano, José Ramón, David Alaminos, Francisco García-Lagos, and Angela M. Callejón-Gil. 2020. "Predicting Audit Opinion in Consolidated Financial Statements with Artificial Neural Networks" Mathematics 8, no. 8: 1288. https://doi.org/10.3390/math8081288