Resources and Toolkits

Video outlining best practices for states to improve their risk assessment and error detection processes, including model design, review sequencing, feature engineering, review process optimization, and quick wins

Workshop examining how predictive analytics and risk scoring can improve SNAP implementation and evaluation, using Conneticut as a case study.

Workshop to foster collaboration and share modeling practices among state agencies in response to HR1’s new SNAP PER cost share requirements. Gathering encompassed convened a group of nearly 40 research and data analytics staff from across 15 states involved in SNAP QC data modeling.

Key strategies to improve accuracy and efficiency of SNAP program delivery, including evaluating intervention impacts independently, developing strong proxy metrics, watching for unintended consequences, strategically reviewing most error-prone case elements and actions, leveraging new technology for caseworkers, and improving client communication and outreach.