A Cost-Effective Tiered Proctoring Framework for Machine Learning-Based Risk Assessment of Cheating in Examination Monitoring

Key Points

• The framework demonstrates a significant reduction in cheating incidents during examinations, potentially improving academic integrity.
• Using machine learning algorithms, the proposed system efficiently assesses risks associated with examination monitoring techniques.
• This observational analysis establishes a tiered proctoring framework, integrating data analysis techniques for effective cheating detection.
• Supports the notion that cost-effective solutions can bolster exam integrity, though external validation is warranted.