Conceptual Modeling and Semantic Relations in the Construction of Financial Knowledge Graphs
DOI:
https://doi.org/10.71222/evj1tt66Keywords:
financial knowledge graph, conceptual modeling, semantic relations, ontology, financial data, knowledge representationAbstract
Financial Knowledge Graphs (FKGs) are increasingly recognized as essential tools for managing and leveraging financial data. This review paper explores the conceptual modeling approaches and semantic relations crucial for their construction. We begin by providing a historical overview of knowledge representation in finance, tracing the evolution from early expert systems to contemporary FKGs. The core of the paper delves into two critical themes: (A) conceptual modeling techniques, including ontologies, entity-relationship diagrams, and semantic networks, and their application to financial data; and (B) the types and roles of semantic relations (e.g., is-a, part-of, influences) in connecting financial entities and concepts. We then present a comparative analysis of these modeling techniques, highlighting their strengths, weaknesses, and challenges in capturing the complexities of financial information. Furthermore, we address the unique challenges of constructing FKGs, such as data heterogeneity, ambiguity, and the dynamic nature of financial markets. The review concludes by discussing promising future research directions, including the integration of machine learning techniques for automated knowledge graph construction and the development of novel semantic relation discovery methods. This paper serves as a comprehensive guide for researchers and practitioners interested in the design and implementation of effective FKGs for various financial applications.References
1. C. Peng, F. Xia, M. Naseriparsa, and F. Osborne, “Knowledge graphs: Opportunities and challenges,” Artif. Intell. Rev., vol. 56, no. 11, pp. 13071-13102, 2023.
2. A. Chis, “Applying management theories as a conceptualization lens for knowledge graphs and conceptual modeling methods,” in BIR Workshops, 2023, pp. 257-270.
3. Z. Ge, “Knowledge graphs and its applications in finance,” The Future and Fintech: ABCDI and Beyond, pp. 155-214, 2022.
4. A. Hur, N. Janjua, and M. Ahmed, “A survey on state-of-the-art techniques for knowledge graphs construction and challenges ahead,” in 2021 IEEE Fourth International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), 2021, pp. 99-103.
5. Z. Liu, S. Chen, and Z. Zhang, “Construction of Financial Event Knowledge Big Graph: An Event-Driven Knowledge Organization Framework,” in Knowledge Organization for Resilience in Times of Crisis: Challenges and Opportunities, 2024, pp. 89-100.
6. S. Prakash, “Demystifying Knowledge Graphs for AI-Enhanced Financial Decision Support with Graph Neural Networks,” J. Comput. Sci. Technol. Stud., vol. 7, no. 6, pp. 580-590, 2025.
7. M. Schröder et al., “Towards Cyber Mapping the German Financial System with Knowledge Graphs,” in European Semantic Web Conference, 2024, pp. 270-288.
8. S. Elhammadi, Financial knowledge graph construction, Doctoral dissertation, University of British Columbia, 2020.
9. Z. Xu, H. Takamura, and R. Ichise, “FinCaKG: A Framework to Construct Financial Causality Knowledge Graph from Text,” Int. J. Semantic Comput., pp. 1-20, 2025.
10. S. B. Viswanathan and G. Singh, “Advancing financial operations: leveraging knowledge graph for innovation,” Int. J. Comput. Trends Technol, vol. 71, no. 10, pp. 51-60, 2023.
11. Z. Xu and R. Ichise, “FinCaKG-Onto: the financial expertise depiction via causality knowledge graph and domain ontology,” Appl. Intell., vol. 55, no. 6, pp. 1-17, 2025.
12. S. Zehra, S. F. M. Mohsin, S. Wasi, S. I. Jami, M. S. Siddiqui, and M. K. U. R. R. Syed, “Financial knowledge graph based financial report query system,” IEEE Access, vol. 9, pp. 69766-69782, 2021.
