This paper explores the potential of using machine learning and modern data science to enhance the impact of justice processes. The authors argue that traditional cost-benefit analysis is limited in its ability to capture the heterogeneity of benefactors and beneficiaries and that a more nuanced approach is needed. The paper outlines a method for incorporating a heterogeneous component into an existing cost-benefit analysis app, which takes into account social group or population-specific variation, differences in justice processes across groups, and the distribution of costs and benefits. The authors also suggest the use of empirically informed statistical techniques to gain new insights from data and maximize the impact for beneficiaries. Overall, the paper provides a promising approach for improving the effectiveness of justice processes through the use of modern data science techniques.