A substantial and powerful literature in statistics and computer science has clearly demonstrated that modern machine learning procedures can forecast more accurately than conventional parametric statistical models such as logistic regression. Yet, several recent studies have claimed that for criminal justice applications, forecasting accuracy is about the same. In this article, we address the apparent contradiction. Forecasting accuracy will depend on the complexity of the decision boundary. When that boundary is simple, most forecasting tools will have similar accuracy. When that boundary is complex, procedures such as machine learning, which proceed adaptively from the data, will improve forecasting accuracy, sometimes dramatically. Machine learning has other benefits as well, and effective software is readily available.
The complexity of the decision boundary will in practice be unknown, and there can be substantial risks to gambling on simplicity. Criminal justice decision makers and other stakeholders can be seriously misled with rippling effects going well beyond the immediate offender. There seems to be no reason for continuing to rely on traditional forecasting tools such as logistic regression.