A Hybrid Framework for Master Data Management: Integrating Machine Learning and Traditional Approaches

EasyChair Preprint no. 12470

Abstract

Master Data Management (MDM) plays a crucial role in organizations by ensuring consistency and accuracy in critical data assets. However, the complexity and scale of modern data environments often challenge traditional MDM frameworks. In response, this paper proposes a Hybrid Framework for Master Data Management that integrates machine learning techniques with traditional approaches to enhance data quality, scalability, and agility. Leveraging the strengths of both paradigms, this framework aims to address the limitations of conventional MDM systems while embracing the opportunities offered by advanced analytics and automation. Through a comprehensive literature review, we identify key challenges in MDM and review state-of-the-art techniques in both traditional and machine learning-based approaches. We then present our proposed Hybrid Framework, detailing its architecture, components, and implementation strategies.

Keyphrases: data, management, Master

@Booklet{EasyChair:12470,
  author = {Chen Liu and Julia Anderson},
  title = {A Hybrid Framework for Master Data Management: Integrating Machine Learning and Traditional Approaches},
  howpublished = {EasyChair Preprint no. 12470},

  year = {EasyChair, 2024}}