Goltz, N., & Mayo, M. (2017). Enhancing regulatory compliance by using artificial intelligence text mining to identify penalty clauses in legislation. Presented at the MIREL 2017 - Workshop on ‘Mining and REasoning with Legal texts’, held in conjunction with the 16th International Conference on Artificial Intelligence and Law, King’s College, London, UK.
Permanent Research Commons link: https://hdl.handle.net/10289/11940
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.
© 2017 copyright with the authors.