نوع مقاله : مقاله پژوهشی
نویسنده
بازرسی کل استان اردبیل
کلیدواژهها
عنوان مقاله English
نویسنده English
This research adopts a descriptive-analytical approach to examine the challenges of economic corruption in Iran's government contracts and proposes a novel solution based on machine learning for identifying corruption-prone anomalies. By analyzing documents and supervisory reports from 2002 to 2021, structural deficiencies in the public procurement system were identified, including ambiguity in legal jurisdictions, lack of integrated systems, extensive managerial discretion, and budgetary non-transparency. The Random Forest model has been introduced as a non-parametric tool for analyzing complex patterns in relationships between stakeholders (such as sham tenders or abnormal concentration of resources). Findings indicate that leveraging machine learning and real-world data from systems like "Setad" leads to the development of an advanced system for monitoring government contracts. This system not only tracks violations (like unusual collaborations) but also enables preemptive intervention by detecting early warning indicators. Despite data limitations, this approach can significantly enhance transparency and accountability in the utilization of Iran's public resources.
کلیدواژهها English
