The Role of Artificial Intelligence Techniques in Enhancing External Auditors’ Efficiency in Detection Financial Fraud: An Empirical Study | ||||
| مجلة الدراسات التجارية المعاصرة | ||||
| Articles in Press, Accepted Manuscript, Available Online from 06 August 2025 | ||||
| Document Type: المقالة الأصلية | ||||
| DOI: 10.21608/csj.2025.407131.1644 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
هدير هشام السيد إبراهيم  ; سماح طارق أحمد حافظ; دنيا سمير محمود عبد الرازق
| ||||
| كلية التجارة - جامعة المنصورة | ||||
| Abstract | ||||
| The escalating complexity of financial fraud has rendered traditional detection mechanisms inadequate, compelling the adoption of AI-driven solutions. By leveraging predictive algorithms, anomaly identification systems, and machine intelligence, AI transforms fraud prevention into a dynamic, adaptive defense framework. The research aimed to evaluate the impact of using artificial intelligence techniques on improving the efficiency of external auditors in detecting financial fraud, through examining the impact of adopting decision tree classification, support vector machine classification, K-Nearest Neighbors classification, and Random Forest classification, on the external auditing and on the efficiency of external auditors in detecting financial statement fraud. The research relies on a sample of non-financial companies listed on the Egyptian Stock Exchange, which numbers 126 companies in different sectors. This study depends on 1000 firm-year observations from the Egyptian environment through the period 2012 to 2022. The researchers found that there is a significant impact of adopting artificial intelligence techniques (e.g., decision tree classification, support vector machine classification, K-Nearest Neighbors classification, and Random Forest classification) on the external auditing and on the efficiency of external auditors in detecting financial statement fraud. | ||||
| Keywords | ||||
| Decision tree classification; support vector machine classification; K-Nearest Neighbors classification; and Random Forest classification; Detecting Financial Fraud | ||||
|
Statistics Article View: 29 |
||||
