The impact of machine learning on audit risk assessment: evidences from Egypt

نوع المستند : المقالة الأصلية

المؤلفون

1 كليه تجاره جامعه كفرالشيخ

2 كلية التجارة -جامعة كفر الشيخ

3 كليه التجاره، جامعه كفر الشيخ

المستخلص

This study investigates how machine learning contributes to the evaluation of audit risks in Egypt, using a structured two-phase approach. The theoretical phase involved a comprehensive review of relevant literature to form a conceptual foundation. The practical phase focused on hypothesis testing through data analysis, using a survey distributed to 192 participants, including academic experts and practicing auditors. The empirical results demonstrated that machine learning has a significant influence on assessing inherent risk, control risk, and detection risk—the key components of audit risk. These outcomes provided sufficient evidence to reject the null hypothesis, which suggested that machine learning does not significantly affect audit risk assessment. Instead, the acceptance of the alternative hypothesis confirmed machine learning's considerable impact. This underscores the growing importance of technological integration in auditing, particularly the value of intelligent systems in enhancing precision, streamlining audit procedures, and proactively identifying risk factors. The findings support the notion that audit processes can be substantially improved through the adoption of machine learning tools, marking a shift toward more efficient, data-driven approaches in the auditing profession.

الكلمات الرئيسية

ملفات

شارك

إرسال الاستشهاد إلى

الإحصائيات