Forecasting criminal sentencing decisions

This paper investigates the feasibility of developing bootstrapping models of criminal sentencing decisions to predict sentence length and the outcome of sentencing appeals. New Zealand Court of Appeal sexual offence sentencing decisions are modelled as a function of variables describing the character of the offender and the circumstances of the offence. The model outperforms both an equal weights approach and a naive mean projection in predicting sentence lengths in a holdout sample. As applications and further validations of the model, the disparity between actual and predicted sentence is used to forecast the success of an appeal and to predict change in sentence, given a successful appeal. The results confirm that bootstrapping models have the potential to contribute to a field traditionally believed to favour solely judgemental approaches.