In early July, a team of NYU CUSP master’s students partnering with BetaGov presented data analysis and visualization to the Santa Clara County (CA) District Attorney’s Office. Their analysis is helping the office understand the factors influencing case-processing time and develop ideas for improving the process. This capstone had two goals: to create a visualization tool that facilitates the DA’s office exploration of their own data and analytical models that identify drivers of prosecutorial delays.
The visualization tool allows a comparison of five phases of the prosecutorial process for SCC criminal cases: case issuing to arraignment, arraignment to preliminary trial, preliminary trial to plea, plea to disposition, and post-disposition court events. It enables aggregation, filtering, and extraction of prosecution-related statistics (e.g., crime type, number of defendants on case, number of charges) and demographics (e.g., race/ethnicity, gender, age). It is designed to run in the CUSP computational environment, assuring protection of identifiable data.
The prosecution duration and outcome are modeled with decision-tree algorithms (random forest and gradient-boosted trees). The models enable identifying the most significant features associated with prosecutorial delays, and assessing the importance of demographics in prosecution duration and outcome.