Application of data mining in assessing the level of corporate social responsibility disclosure compliant with financial performance and accounting criteria

Document Type : Research Paper


1 Department of Accounting, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran

2 Department of Accounting, University of Isfahan, Isfahan, Iran

3 Department of Economics, University of Isfahan, Isfahan, Iran

4 Department of Computer, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran


Utilizing new models instead of traditional statistical models can be quite useful in this field. Examples include data mining, which possesses both high speed and accuracy as well as nonlinear and non-parametric properties Therefore, in the present study, the effects of performance criteria on social responsibility disclosure level was investigated and analyzed via utilization of data mining, Henceforth, a model will be presented aiming to estimate/project the optimal level of social responsibility disclosure grounded on performance criteria. The present study is applied in terms of its nature and purpose/objective as well as based on the field research method of data collection. The statistical population are companies listed on the Tehran Stock Exchange and the required data were collected and analyzed using six data mining methods during the 2013-2019 period. The findings reveal it is possible to classify and predict the optimal level of corporate social responsibility disclosure within the Iranian economic circumstances/environment. Moreover, the utilization of the classification algorithm in the vicinity of the nearest neighbor can accurately predict the optimal level of corporate social responsibility disclosure based on performance criteria. The findings of this study indicate that performance metrics can be a positive predictor of the optimal level of corporate social responsibility disclosure. In addition, due to the potent strength of the proposed model, the used model in this research can be utilized to rank/rate the level of corporate social responsibility disclosure.


[1] W. Abbott and R.J. Monsen, On the measurement of corporate social responsibility: Self reported disclosures as
a method of measuring corporate social involvement, Acad. Manag. J. 1979 (1979), no. 22, 501–515.
[2] R. Agarwal and E. Karahanna, Time flies when you’re having fun: Cognitive absorption and beliefs about information technology usage, MIS Quart. 24 (2000), 665–694.
[3] A.M. Alimohamadi, A.M. Abbasimehr and A. Javaheri, Prediction of stock return using financial ratios: A
decision tree approach, Financ. Manag. Strategy 3 (2016), no. 11, 125–146.
[4] A. Alivandi Darani, M. Arabsalehi , H. Amiri and F. Zamani Boroojeni, Validation tool for assessing the level
of disclosure of corporate social responsibility for the companies listed on the Tehran Stock Exchange, J. Health
Account. 9 (2020), no. 1, 78–100.
[5] F.A. Amani and A.M. Fadlalla, Data mining applications in accounting: A review of the literature and organizing
framework, Int. J. Account. Inf. Syst. 24 (2017), 32–58.
[6] D. Appelbaum, A. Kogan, M. Vasarhelyi and Z. Yan, Impact of business analytics and enterprise systems on
managerial accounting, Int. J. Account. Inf. Syst. 25 (2017), 29–44.
[7] M. Arabmazar Yazdi, A. Nasseri, M. Nekoee Zadeh and A. Moradi, The impact of accounting information system
flexibility on firm performance with dynamic capabilities approach, Account. Audit. Rev. 24 (2017), no. 2, 221–242.
[8] P. Chalaki and M. Yosefi, Predicting earnings management using the decision tree, Account. Audit. Stud. 1 (2012),
no. 1, 110–123.
[9] P.M. Clarkson, Y. Li, G.D. Richardson and F.P. Vasvari, Does it really pay to be green? Determinants and
consequences of proactive environmental strategies, J. Account. Public Policy 30 (2011), no. 2, 122–144.
[10] D. Cormier and M. Magnan, Environmental reporting management: A Europeanperspective, J. Account. Public
Policy 22 (2003), no. 1, 43–62.
[11] F. Daniel, F. Lohrke, C. Fornaciari and A. Turner, Slack resources and firm performance: A meta-analysis, J.
Bus. Res. 57 (2004), no. 6. 565–574.
[12] M. Dastgir and M. Shafiei Sardashti Data mining, a new Approach in financial field, Auditor 11 (2011), no. 5,
[13] N.C.P. Edirisinghe and X. Zhang, Portfolio selection under DEA-based relative financial strength indicators:
Case of US industries, J. Oper. Res. Soc. 59 (2008), no. 6, 842–856.
[14] H. Etemadi, R. Hesarzadeh, M. Mohammadabadi and A. Bazrafshan, Disclosure and firm value: Evidence from
Iran’s Emergence Stock Market, Manag. Account. 5 (2015), no. 13, 67–77.
[15] J.R. Evans, Business Analytics: Methods, models, and decisions, Prentice-Hall, Boston, MA, 2013.
[16] P. Everaert, Discovering patterns in corporate social responsibility (CSR) reporting: A transparent framework
based on the Global Reporting Initiative’s (GRI) SustainabilityR eporting Guidelines, Faculty of Economics and
Business Administration, Ghent University, Belgium, 2009.
[17] S.L. Hart, A natural resource based view of the firm, Acad. Manag. Rev. 20 (1995), no. 4, 986–1014.
[18] B.J. Inchausti, The influence of company characteristics and accounting regulation on information disclosed by
Spanish firms, Eur. Account. Rev. 6 (1997), no. 1, 45–68.[19] H. Jiawei, M. Kamber and J. Pei, Data mining: Concepts and techniques, 3rd edition, Morgan Kaufmann, 2011.
[20] A.F. Jurkus, J.C. Park and L.S. Woodard, Women in top management and agency costs, J. Bus. Res. 64 (2011),
no. 2, 180–186.
[21] L. Kozma, K Nearest neighbor algorithm (Knn), Helsinki University of Technology, Special Course in Computer
and Information Science, Available online at:, 2008.
[22] H. Li, J. Sun and J. Wu, Predicting business failure using classification and regression tree: An empirical comparison with popular classical statistical methods and top classification mining methods, Expert Syst. Appl. 37
(2010), no. 8, 5895–5904.
[23] J. Luo, M. Meng and C. Yan, Analysis of the impact of artificial intelligence application on the development of
accounting industry, Open J. Bus. Manag. 2018 (2018), no. 6, 850–856.
[24] G. Mahdavi, A. Daryaei, R. Alikhani and M. Maranjory, The relation of firm size, industry type and profitability
to social and environmental information disclosure, Empir. Res. Account. 4 (2015), no. 3, 87–103.
[25] G.H. Mahdavi and A. Ghahramani, Providing a pattern of fraud detection by auditors using artificial neural
network, Audit Sci. 7 (2015), no. 67, 45–70.
[26] S.M.S. Mousavi Nasab, Hypothesis; Where is it necessary?, Res. 3 (2011), no. 2, 5–14.
[27] A. Owusu-Ansah, Timeliness of corporate financial reporting in emerging capital markets: Empirical evidence
from the Zimbawe Stock Exchange, Account. Bus. Res. 30 (2000), no. 3, . 241–254.
[28] D.M. Patten, Media exposure, public policy pressure, and environmental disclosure: An examination of the impact
of TRI data availability, Account. Forum 26 (2002), no. 2, 152–171.
[29] M. Namazi and R. Gholami, Comprehensive ranking model of companies via accounting information, balanced
scorecard and PAPRIKA technique, Account. Knowledge 7 (2017), no. 27, 7–33.
[30] M. Namazi and N.R. Namazi, Ranking firms based on the performance evaluation criteria via multiple attribute
TOPSIS technique and comparing evaluation criteria (Evidence from companies listed in Tehran Stock Exchange),
Financ. Account. Res. 8 (2016), no. 2, 39–64.
[31] G. Perriere and J. Thioulouse, Use of correspondence discriminant analysis to predict the subcellular location of
bacterial proteins, Comput. Meth. Prog. Biomed. 2003 (2003), no. 70, 99–105.
[32] Y. Qiu, A. Shaukat and R. Tharyan, Environmental and social disclosures: Link with corporate financial performance, Br. Account. Rev. 48 (2016), no. 1, 102–116.
[33] M. Rodriguez-Fernandez, Social responsibility and financial performance: The role of good corporate governance,
BRQ Bus. Res. Quart. 19 (2016), no. 2, 137–151.
[34] M.V. Russo and P.A. Fouts, A resource-based perspective on corporate environmental performance and profitability,
Acad. Manag. J. 40 (1997), no. 3, 534–559.
[35] M. Salehi and L. Farrokhi Pilehrood, Predicting earnings management using neural network and decision tree,
Financ. Account. Audit. Res. 10 (2017), no. 37, 1–24.
[36] H. Servaes, and A. Tamayo, The impact of corporate social responsibility on firm value: The role of customer
avareness, Manag. Sci. 59 (2013), no. 5, 1045–1061.
[37] S. S. Singhavi and H. B. Desai, An empirical analysis of the quality of corporate financial disclosure, Account.
Rev. 46 (1971), no. 1, 129–138.
[38] A. Skouloudis, K. Evangelinos and F. Kourmousis, Assessing non-financial reports according to the global
reporting initiative guidelines: Evidence from Greece, J. Clean. Prod. 18 (2010), no. 5, 426–438.
[39] A. Soroushyar and M. Akhlaghi, The comparative assessment of data mining methods effectiveness to forecasting
return and risk of stock in companies Listed in Tehran Stock Exchange, Financ. Account. Res. 9 (2017), no. 1,
[40] J. Sun and H. Li, Data mining method for listed companies’ financial distress prediction, Knowledge-Based Syst.
21 (2008), no. 1, 1–5.[41] C. F. Tsai and Y. J. Chiou, Earnings management prediction: A pilot study of combining neural networks and
decision trees, Expert Syst. Appl. 36 (2009), no. 3, 7183–7191.
[42] R. Verrecchia, Essays on disclosure, J. Account. Econ. 32 (2001), no. 1-3, 97–180.
[43] Y. Hassas Yeganeh and G. Barzegar, Identifying the components and indicators of corporate social responsibility
in Iran, Soc. Cult. Dev. Stud. 2 (2013), no. 1, 209–234.
[44] X.Z. Zhang, Y. Hu, K. Xie, W.G. Zhang, L.J. Su and M. Liu, An evolutionary trend reversion model for stock
trading rule discovery, Knowledge-Based Syst. (2015), no. 79, 27–35.
[45] L.G. Zhou, D. Lu and H. Fujita, The performance of corporate financial distress prediction models with features
selection guided by domain knowledge and data mining approaches, Knowledge-Based Syst. 85 (2015), 52–61.
Volume 13, Issue 2
July 2022
Pages 1937-1951
  • Receive Date: 03 November 2021
  • Revise Date: 19 January 2022
  • Accept Date: 03 February 2022