Explainable Artificial Intelligence for Assault Sentence Prediction in New Zealand
This addresses the need for transparent AI tools in the judiciary to assist with sentence prediction, though it is incremental as it builds on existing explainable AI methods.
The paper tackled the problem of predicting imprisonment sentences for assault cases in New Zealand courts using explainable artificial intelligence, achieving predictions accurate to within one year.
The judiciary has historically been conservative in its use of Artificial Intelligence, but recent advances in machine learning have prompted scholars to reconsider such use in tasks like sentence prediction. This paper investigates by experimentation the potential use of explainable artificial intelligence for predicting imprisonment sentences in assault cases in New Zealand's courts. We propose a proof-of-concept explainable model and verify in practice that it is fit for purpose, with predicted sentences accurate to within one year. We further analyse the model to understand the most influential phrases in sentence length prediction. We conclude the paper with an evaluative discussion of the future benefits and risks of different ways of using such an AI model in New Zealand's courts.