First of, RKG is a linked dataset of Refinitiv financial documents and it consists of over 2 billion facts related to organisations, employees, market deals, and so on. The relations are high heterogeneous, covering different entity relationships. Currently, there are seven content sets:

  1. Equity instruments and quotes – 30 million equity instruments and 80 million quotes

  2. Organisations – 5 million organisations with 1.1 million hierarchy relationships

  3. Supply chain – 35K companies and 55K relationships

  4. Related companies

  5. Officers and Directors – 2.5 million+ people

  6. Deals – Over 280K investments and 1.5 million M&A

  7. Financial taxonomies and metadata

All the data items in RKG are referenced using PermID, a permanent machine-readable identifier. This makes it easier to handle complex data structures and eliminating any inconsistencies in mappings, making the whole workflow a lot more efficient.



Data Scientist

Leave a Reply