Developing and Deploying Methodologies for Improving the Accuracy, Fairness, and Trustworthiness of Risk Assessment Models in Child Welfare
It is estimated that that child protection agencies across the US receive over 4 million referral calls per year. The practice of screening calls is left to each jurisdiction to follow local practices and policies, potentially leading to large variation in the way in which referrals are treated across the country. While increased access to linked administrative data is available, it is difficult for child welfare workers to make systematic use of historical information about all the children and adults on a single referral call. Predictive analytics offers a way forward. By building risk assessment models using routinely collected administrative data, we can better identify cases that are the most likely to result in adverse child welfare outcomes. This information could then be supplied to call workers in real time to help them prioritize cases for investigation or other services.
At this point in time, however, the use of risk assessment in the child welfare domain remains contentious, largely untested, and distrusted by many. This proposal aims to contribute toward developing and deploying methodologies for improving the accuracy, fairness, and trustworthiness of risk assessment models in child welfare.
Maria De-Arteaga, PhD Candidate in Machine Learning & Public Policy