This paper explains the science underlying risk-based decision-making and explores both the promise and controversies associated with the increasing application of “big data” to the field of criminal justice. While the technology has contributed to important policy reforms, such as the diversion of low-risk groups from jail and prison, debate has arisen over the potential for risk assessments to reproduce existing racial biases, the lack of transparency of some proprietary tools, and the challenge of applying classifications based on group behavior to individual cases. Along with identifying an emerging professional consensus that the careful and ethical implementation of risk assessment tools can improve outcomes, the paper closes with a series of best practices urging jurisdictions adopt a localized, collaborative approach.