Automated Decision Support for Financial Regulatory/Policy Compliance, using Textual Rulelog

tags

Rules as Code

Notes

Automated support is needed for compliance decisions and associated analysis

NOTER_PAGE: (2 . 0.145550972304066)

require humans in the loop at run time, often be- cause the scope of automation only captures part of the substance

NOTER_PAGE: (2 . 0.20329994107248084)

The regulations (and associated policies) are frequently very compli- cated in both their logical/semantic substance and their English syntax

NOTER_PAGE: (2 . 0.6087212728344137)

important excep- tion cases requiring defeasibility

NOTER_PAGE: (2 . 0.63877430760165)

full of meta information

NOTER_PAGE: (2 . 0.6399528579846788)

reasoning efficiency (near real time) are necessary

NOTER_PAGE: (2 . 0.6823806717737183)

provenance

NOTER_PAGE: (2 . 0.6823806717737183)

Starting from English source sentences in published regulations and other documents, we ar- ticulated a set of English encoding sentences that were clearer and syntactically more self-contained

NOTER_PAGE: (3 . 0.4348850913376547)

each English phrase is mapped closely (nearly iso- morphically) to and from a corresponding Ergo logical term

NOTER_PAGE: (3 . 0.5085444902769594)

inferencing is worst-case polynomial-time

NOTER_PAGE: (3 . 0.7495580436063641)

scales up to millions, but not billions, of complex infer- ences and associated dependencies and fact assertions

NOTER_PAGE: (4 . 0.21803182086034179)

“@@{defeasible}” means the rule can have exceptions.

NOTER_PAGE: (6 . 0.7253977607542722)

transparency afforded by our approach has the potential to signif- icantly improve the governance of the process of writing and enforcing regulations

NOTER_PAGE: (8 . 0.2575132586918091)