A neural network for speedy trials

In recent years, the case loads of judges have increased, while speedy trial laws place a time limit between the defendant's arrest and trial dates. Because of this time constraint, it seems that for minor cases, judges pass sentences based on a set of certain factors (patterns) not based on the individual merits of each case. Patterns may be learned by a neural network. In this paper, we investigate the credibility of the neural network approach as a viable tool in the sentencing process and we show its superiority over the ID3 approach.