Automating Regulation W
In our latest addition to the Ergo Examples Bank, we show how to automate a complex banking regulation, Regulation W, in Ergo . The knowledge and rule base in the example is an updated version of the one used for the Enterprise Data Management Council (EDMC) sponsored FIBO rules pilot that targeted decision automation for financial regulations. Coherent’s Benjamin Grosof was the technical lead for the PoC which included Wells Fargo Bank, SRI International, and the Governance, Risk and Compliance Technology Centre (GRCTC, Ireland). The PoC included leveraging EDMC’s FIBO (the Financial Industry Business Ontology), an emerging ‘common language’ for automation of business processes across the financial industry to create semantic business rules capable of deep reasoning.
The thoroughly commented example shows how the regulation text can be represented in Ergo’s logical syntax, including the chain of reasoning needed to identify whether a given transaction is in compliance with the regulation. Example queries and answers are included as illustrations.
Features of Ergo illustrated in the example include:
- Ergotext: Enables one to do knowledge entry using controlled English-like sentences.
- Exception cases and prioritization: Create an exception rule that overrides the general case when appropriate conditions are met.
- Multi-step, complex reasoning: The rule and knowledge base shows how to encode a regulation that contains complex banking and legal rules with multiple steps of reasoning.
- Explanations: Explanations can be generated for each query answer, making transparent the logical chain of reasoning that resulted in the answer. Also very useful for checking and debugging a rulebase.