Why KGs for financial services?

Data is growing rapidly and data aggregation and management has become an increasingly challenging problem. The goal of data management is to provide business analysts with the data they need, when they need it. This means that the data must be of high quality, timely, and accurate and consistent across different types of data: structured, semi-structured, and unstructured.

What is a knowledge graph (KG)?

A KG is a conceptual model of the world, representing it using entities as nodes and relationships as edges. The Financial Industry Business Ontology (FIBO) is an example of a business conceptual mode for the finance industry. Knowledge graphs accept and aggregate data from many different sources. Combining these data is one of the major challenges of KGs. Figure below showcase the process of aggregation and projection of KGs.

What are some of the deployment patterns for semantic data fabrics?
  1. Provide self-service access to complex data across many sources

  2. Provide a semantic layer of data management on data lakes

  3. Accelerate and automate data preparation for AI projects

What are some of the real world use cases for enterprise KGs?
  1. Alternative data for analytics and machine learning in search of alpha

  2. Interest rate swap risk analytics

  3. Trade surveillance

  4. Fraud analytics, transforming transactional data into a social view

  5. Feature engineering and selection for AI projects

  6. Data migration

Ryan

Ryan

Data Scientist

Leave a Reply