Enhancing Regulatory Compliance by Using Artificial Intelligence Text Mining to Identify Penalty Clauses in Legislation

MIREL 2017 - Workshop on `MIning and REasoning with Legal texts' - June 16th, 2017 - London (UK)

9 Pages Posted: 4 Jun 2017

See all articles by Nachshon Goltz

Nachshon Goltz

Edith Cowan University

Michael Mayo

University of Waikato

Date Written: May 30, 2017

Abstract

As regulatory compliance (or compliance governance) becomes ever more challenging, attempts to engage IT solutions and especially artificial intelligence (AI) are on the rise. This paper suggest that regulatory compliance can be enhanced by employing an AI model trained to identify penalty clauses in the regulations. The paper provides the theoretical basis of machine learning for text classification and presents a two stage experiment of (1) training multiple models and selecting the best one; and (2) employing a sliding window detection in order to identify penalty clauses in regulation. Results benchmarked using an algorithm based penalties API suggests further development is needed.

Keywords: Regulatory compliance, Artificial Intelligence, Text mining, Penalties, Machine learning

Suggested Citation

Goltz, Nachshon and Mayo, Michael, Enhancing Regulatory Compliance by Using Artificial Intelligence Text Mining to Identify Penalty Clauses in Legislation (May 30, 2017). MIREL 2017 - Workshop on `MIning and REasoning with Legal texts' - June 16th, 2017 - London (UK). Available at SSRN: https://ssrn.com/abstract=2977570

Nachshon Goltz (Contact Author)

Edith Cowan University ( email )

Australia

Michael Mayo

University of Waikato ( email )

Te Raupapa
Private Bag 3105
Hamilton, 3240
New Zealand

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
272
Abstract Views
893
rank
116,579
PlumX Metrics