The article presents ‘Prismatic’, a visual analytics system designed for financial cluster analysis. Prismatic facilitates the understanding of business correlations by integrating quantitative analysis of historical performance and qualitative analysis of business relational knowledge. It features three clustering processes: dynamic cluster generation, knowledge-based cluster exploration, and correlation-based cluster validation. The system utilizes a multi-view clustering approach to enrich data-driven clusters with knowledge-driven similarity. Through well-coordinated visual views, Prismatic provides a comprehensive interpretation of intertwined quantitative and qualitative features. The article demonstrates the usefulness and effectiveness of Prismatic through case studies on formulating concept stocks and extensive interviews with domain experts.
Publication date: 15 Feb 2024
Project Page: N/A
Paper: https://arxiv.org/pdf/2402.08978
