A TRANSPARENT AI-BASED FRAMEWORK FOR PROACTIVE DATA-QUALITY RISK MONITORING IN DIGITAL INFORMATION SYSTEMS
Keywords:
artificial intelligence, data quality, explainable AI, digital information systems, anomaly detection, schema drift, proactive monitoring.Abstract
Reliable data is a key resource for digital organizations, because management dashboards, educational platforms, online services and automated decision systems depend on correct operational records. This article proposes an explainable artificial intelligence framework for proactive data-quality risk monitoring in digital information systems. The model combines completeness, validity, uniqueness, timeliness, distribution drift and anomaly evidence into a transparent risk score. Unlike traditional validation rules, the proposed framework explains the main causes of the warning and recommends remediation actions. A scenario-based analytical evaluation shows that the framework improves early recognition of data-quality degradation and reduces false alerts compared with single-factor monitoring methods.
References
1. Nurjabova D., Sayyora Q., Gulmira P. Using Discretization and Numerical Methods of Problem 1D-3D-1D Model for Blood Vessel Walls with Navier-Stokes //International Conference on Next Generation Wired/Wireless Networking. – Cham : Springer Nature Switzerland, 2022. – С. 73-82.
2. ugli Norboev B. U. et al. Artificial Intelligence in Education and the Digital Preconditions of Tertiary Expansion in Uzbekistan: ARDL Evidence from 2000–2023. – 2026.
3. Ochilova S., Berdiyev G., Xujaqulov N. Fraktal nazariyasiga asoslangan musiqa kompozitsiyasining tahliliy usullari //Journal of Transport. – 2025. – Т. 2. – №. 3. – С. 136-139
4. Rashidovich B. G. DESIGNING FRACTAL BUILDINGS USING ITERATIVE FUNCTION SYSTEMS.
5. Alimov U., Zohirov Q., Berdiyev G. WAYS TO DEVELOP COORDINATION SKILLS IN KURASH //Mental Enlightenment Scientific-Methodological Journal. – 2024. – Т. 5. – №. 09. – С. 9-14.
