MACHINE LEARNING-DRIVEN DATA QUALITY MANAGEMENT IN CRM SYSTEMS: A SYSTEMATIC REVIEW OF AUTOMATED CLEANSING AND ENRICHMENT METHODOLOGIES

Abstract

Machine learning applications in automated data cleansing and enrichment are transforming Customer Relationship Management (CRM) systems, offering unprecedented opportunities for improving data quality and operational efficiency. This systematic review examines the evolution, implementation, and impact of machine learning-driven approaches to data management in enterprise CRM environments. The article analyzes key aspects of automated data cleansing, including duplicate detection, standardization of formats, and pattern recognition, while also exploring the capabilities of machine learning in data enrichment through intelligent integration of third-party sources. The article demonstrates that ML-based automation significantly reduces manual intervention requirements while improving accuracy in data management processes. The findings indicate substantial improvements in data quality, operational efficiency, and decision-making capabilities when compared to traditional manual approaches. However, the study also identifies important considerations regarding data privacy, technical implementation challenges, and system integration requirements. This article contributes to the growing body of knowledge on intelligent data management and provides practical insights for organizations seeking to leverage machine learning for CRM data quality enhancement. The article concludes with recommendations for implementation and suggestions for future research directions in this rapidly evolving field.