Prismatic: Interactive Multi-View Cluster Analysis of Concept Stocks

2024-02-14

arXiv.org

AI Summary

Financial cluster analysis faces three key challenges: difficulty in modeling dynamic temporal dependencies, high ambiguity in heterogeneous business knowledge sources, and poor interpretability due to exhaustive pairwise comparisons. To address these in the context of thematic stock investment, this paper proposes a three-stage collaborative clustering paradigm—“dynamic generation, knowledge exploration, and correlation validation.” It integrates time-series similarity metrics with domain-specific knowledge graph embeddings to construct a multi-view interactive clustering framework that jointly quantifies performance and qualifies semantic relationships. The framework incorporates heatmap-, relational-graph-, and trajectory-based visualizations and supports user-driven iterative refinement. Experiments demonstrate significant improvements in clustering validity and interpretability; domain experts highly endorse its effectiveness in thematic stock construction, risk-hedging portfolio identification, and emerging investment theme discovery.

Technology Category

• Machine Learning: Clustering
• Data Mining & Knowledge Management: Data Visualization & Summarization
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Financial cluster analysis allows investors to discover investment alternatives and avoid undertaking excessive risks. However, this analytical task faces substantial challenges arising from many pairwise comparisons, the dynamic correlations across time spans, and the ambiguity in deriving implications from business relational knowledge. We propose Prismatic, a visual analytics system that integrates quantitative analysis of historical performance and qualitative analysis of business relational knowledge to cluster correlated businesses interactively. Prismatic features three clustering processes: dynamic cluster generation, knowledge-based cluster exploration, and correlation-based cluster validation. Utilizing a multi-view clustering approach, it enriches data-driven clusters with knowledge-driven similarity, providing a nuanced understanding of business correlations. Through well-coordinated visual views, Prismatic facilitates a comprehensive interpretation of intertwined quantitative and qualitative features, demonstrating its usefulness and effectiveness via case studies on formulating concept stocks and extensive interviews with domain experts.

Problem

• Dynamic financial cluster analysis across time spans
• Integration of quantitative and qualitative business correlations
• Interactive multi-view clustering for concept stocks

Innovation

• Integrates quantitative and qualitative analysis interactively
• Features dynamic, knowledge-based, correlation-based clustering
• Utilizes multi-view clustering for nuanced understanding