External Audit and Financial Characteristics in Predicting Economic-Sector Membership Using Machine Learning: Evidence from Iraqi Listed Companies
DOI:
https://doi.org/10.71285/icpt.v3i2.39Ключевые слова:
External audit, financial characteristics, economic-sector prediction, machine learning, listed companies, Iraq, audit opinion, sector classificationАннотация
This study investigates the predictive role of external-audit and financial characteristics in identifying economic-sector membership among Iraqi listed companies using machine-learning techniques. The analysis is based on 263 firm-year observations from 33 companies distributed across six verified economic sectors during 2015–2024. Three predictive specifications are evaluated: financial characteristics only, external-audit characteristics only, and a combined model incorporating both information sets. Logistic regression is adopted as the primary classifier and assessed using leakage-free leave-one-company-out cross-validation with class-preserving nested hyperparameter selection. Additional robustness procedures include alternative machine-learning algorithms, company-level aggregation, permutation testing, stratified company-block bootstrap inference, drop-column analysis, and sample-sensitivity tests. The combined model achieved the highest firm-year macro F1-score of 0.321, compared with 0.266 for the financial-only model and 0.242 for the audit-only model. However, the incremental improvement of 0.055 over the financial-only specification was not statistically conclusive, as the 95% bootstrap confidence interval ranged from −0.024 to 0.129. Firm size emerged as the strongest overall predictor, while modified audit opinion and auditor change were the most influential audit-related characteristics. The combined-model advantage was not consistent at the company level or across all alternative classifiers. The findings indicate that both financial and external-audit characteristics contain sector-related predictive information, while highlighting the need for cautious interpretation in small and imbalanced emerging-market samples.
Библиографические ссылки
G. Shmueli, “To explain or to predict?,” Statistical Science, vol. 25, no. 3, pp. 289–310, 2010, doi: 10.1214/10-STS330.
S. Cho, M. A. Vasarhelyi, T. Sun, and C. Zhang, “Learning from machine learning in accounting and assurance,” Journal of Emerging Technologies in Accounting, vol. 17, no. 1, pp. 1–10, 2020, doi: 10.2308/jeta-10718.
J. Krupa and M. Minutti-Meza, “Regression and machine learning methods to predict discrete outcomes in accounting research,” Journal of Financial Reporting, vol. 7, no. 2, pp. 131–178, 2022, doi: 10.2308/JFR-2021-010.
Y. Bao, B. Ke, B. Li, Y. J. Yu, and J. Zhang, “Detecting accounting fraud in publicly traded U.S. firms using a machine learning approach,” Journal of Accounting Research, vol. 58, no. 1, pp. 199–235, 2020, doi: 10.1111/1475-679X.12292.
H. van der Heijden, “Predicting industry sectors from financial statements: An illustration of machine learning in accounting research,” The British Accounting Review, vol. 54, no. 5, Art. no. 101096, 2022, doi: 10.1016/j.bar.2022.101096.
G. S. Waffo Dzuyo, G. Guibon, C. Cerisara, and L. Belmar-Letelier, “Linking industry sectors and financial statements: A hybrid approach for company classification,” in Proc. AAAI Conf. Artificial Intelligence, vol. 39, no. 16, pp. 16444–16452, 2025, doi: 10.1609/aaai.v39i16.33806.
R. R. Forradellas, D. S. Cabrera, L. M. Garay Gallastegui, and S. L. Náñez Alonso, “Characterization of S&P 500 companies by sector using artificial intelligence: Statistical evidence and machine learning application,” The Journal of Finance and Data Science, vol. 12, Art. no. 100193, 2026, doi: 10.1016/j.jfds.2026.100193.
H. Issa, T. Sun, and M. A. Vasarhelyi, “Research ideas for artificial intelligence in auditing: The formalization of audit and workforce supplementation,” Journal of Emerging Technologies in Accounting, vol. 13, no. 2, pp. 1–20, 2016, doi: 10.2308/jeta-10511.
A. Fedyk, J. Hodson, N. Khimich, and T. Fedyk, “Is artificial intelligence improving the audit process?,” Review of Accounting Studies, vol. 27, pp. 938–985, 2022, doi: 10.1007/s11142-022-09697-x.
K. J. Reichelt and D. Wang, “National and office-specific measures of auditor industry expertise and effects on audit quality,” Journal of Accounting Research, vol. 48, no. 3, pp. 647–686, 2010, doi: 10.1111/j.1475-679X.2009.00363.x.
A. Habib and M. B. U. Bhuiyan, “Audit firm industry specialization and the audit report lag,” Journal of International Accounting, Auditing and Taxation, vol. 20, no. 1, pp. 32–44, 2011, doi: 10.1016/j.intaccaudtax.2010.12.004.
Iraq Stock Exchange, “Company Guide.” [Online]. Accessed: Aug. 20, 2026.
T. Martikainen, K. Puhalainen, and P. Yli-Olli, “On the industry effects on the classification patterns of financial ratios,” Scandinavian Journal of Management, vol. 10, no. 1, pp. 59–68, 1994, doi: 10.1016/0956-5221(94)90037-X.
R. Dahlstedt, T. Salmi, M. Luoma, and A. Laakkonen, “On the usefulness of standard industrial classifications in comparative financial statement analysis,” European Journal of Operational Research, vol. 79, no. 2, pp. 230–238, 1994, doi: 10.1016/0377-2217(94)90354-9.
M. N. Angenent, A. P. Pereira Barata, and F. W. Takes, “Large-scale machine learning for business sector prediction,” in Proc. 35th ACM/SIGAPP Symp. Applied Computing (SAC), pp. 1143–1146, 2020, doi: 10.1145/3341105.3374084.
S. Balsam, J. Krishnan, and J. S. Yang, “Auditor industry specialization and earnings quality,” Auditing: A Journal of Practice & Theory, vol. 22, no. 2, pp. 71–97, 2003, doi: 10.2308/aud.2003.22.2.71.
M. Minutti-Meza, “Does auditor industry specialization improve audit quality?,” Journal of Accounting Research, vol. 51, no. 4, pp. 779–817, 2013, doi: 10.1111/1475-679X.12017.
A. Habib, “A meta-analysis of the determinants of modified audit opinion decisions,” Managerial Auditing Journal, vol. 28, no. 3, pp. 184–216, 2013, doi: 10.1108/02686901311304349.
A. Habib, M. B. U. Bhuiyan, H. J. Huang, and M. S. Miah, “Determinants of audit report lag: A meta-analysis,” International Journal of Auditing, vol. 23, no. 1, pp. 20–44, 2019, doi: 10.1111/ijau.12136.
T. Cairney and E. G. Stewart, “Client industry characteristics and auditor changes,” Review of Accounting and Finance, vol. 18, no. 2, pp. 245–267, 2019, doi: 10.1108/RAF-01-2017-0017.
F. Ding, Z. Qiao, M. Hu, and M. Lu, “Industry specialization and audit quality: Evidence from audit firm switches in China,” Asia-Pacific Journal of Financial Studies, vol. 51, no. 5, pp. 657–681, 2022, doi: 10.1111/ajfs.12365.
Q. Wang, T. J. Wong, and L. Xia, “State ownership, the institutional environment, and auditor choice: Evidence from China,” Journal of Accounting and Economics, vol. 46, no. 1, pp. 112–134, 2008, doi: 10.1016/j.jacceco.2008.04.001.
F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
S. Varma and R. Simon, “Bias in error estimation when using cross-validation for model selection,” BMC Bioinformatics, vol. 7, Art. no. 91, 2006, doi: 10.1186/1471-2105-7-91.
L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), pp. 785–794, 2016, doi: 10.1145/2939672.2939785.
C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, pp. 273–297, 1995, doi: 10.1007/BF00994018.
T. M. Cover and P. E. Hart, “Nearest neighbor pattern classification,” IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21–27, 1967, doi: 10.1109/TIT.1967.1053964.
B. Efron, “Bootstrap methods: Another look at the jackknife,” The Annals of Statistics, vol. 7, no. 1, pp. 1–26, 1979, doi: 10.1214/aos/1176344552.
M. Ojala and G. C. Garriga, “Permutation tests for studying classifier performance,” Journal of Machine Learning Research, vol. 11, pp. 1833–1863, 2010.
Загрузки
Опубликован
Как цитировать
Выпуск
Раздел
Лицензия
Copyright (c) 2026 Nadia Talib Salman , Fatimah Fezea Hadab
Это произведение доступно по лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.
