# Beyond Predictive Algorithms in Child Welfare

arXiv: https://arxiv.org/abs/2403.05573 · HTML: https://mlsanity.com/paper/2403.05573/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 114 references that are in the map.
- First posted on arXiv 26 Feb 2024.

## Builds on (most cited first, 21 of 21)

- [Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning](https://mlsanity.com/paper/1609.06570/) (2016)
- [The Fallacy of AI Functionality](https://mlsanity.com/paper/2206.09511/) (2022)
- [Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making](https://mlsanity.com/paper/1802.01029/) (2018)
- [Roles for Computing in Social Change](https://mlsanity.com/paper/1912.04883/) (2019)
- [Improving Human-AI Partnerships in Child Welfare: Understanding Worker Practices, Challenges, and Desires for Algorithmic Decision Support](https://mlsanity.com/paper/2204.02310/) (2022)
- [A Validity Perspective on Evaluating the Justified Use of Data-driven Decision-making Algorithms](https://mlsanity.com/paper/2206.14983/) (2022)
- [A Human-Centered Review of the Algorithms used within the U.S. Child Welfare System](https://mlsanity.com/paper/2003.03541/) (2020)
- [A Framework of High-Stakes Algorithmic Decision-Making for the Public Sector Developed through a Case Study of Child-Welfare](https://mlsanity.com/paper/2107.03487/) (2021)
- [Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders](https://mlsanity.com/paper/2205.08928/) (2022)
- [What If I Don't Like Any Of The Choices? The Limits of Preference Elicitation for Participatory Algorithm Design](https://mlsanity.com/paper/2007.06718/) (2020)
- [Algorithmic Harms in Child Welfare: Uncertainties in Practice, Organization, and Street-level Decision-Making](https://mlsanity.com/paper/2308.05224/) (2023)
- [How we do things with words: Analyzing text as social and cultural data](https://mlsanity.com/paper/1907.01468/) (2019)
- [Modeling Assumptions Clash with the Real World: Transparency, Equity, and Community Challenges for Student Assignment Algorithms](https://mlsanity.com/paper/2101.10367/) (2021)
- [Rethinking "Risk" in Algorithmic Systems Through A Computational Narrative Analysis of Casenotes in Child-Welfare](https://mlsanity.com/paper/2302.08497/) (2023)
- [The Misuse of AUC: What High Impact Risk Assessment Gets Wrong](https://mlsanity.com/paper/2305.18159/) (2023)
- [Unpacking Invisible Work Practices, Constraints, and Latent Power Relationships in Child Welfare through Casenote Analysis](https://mlsanity.com/paper/2203.05169/) (2022)
- [A Human-Centered Review of Algorithms in Homelessness Research](https://mlsanity.com/paper/2401.13247/) (2024)
- [Examining risks of racial biases in NLP tools for child protective services](https://mlsanity.com/paper/2305.19409/) (2023)
- [How to Train a (Bad) Algorithmic Caseworker: A Quantitative Deconstruction of Risk Assessments in Child-Welfare](https://mlsanity.com/paper/2203.05695/) (2022)
- [A Human-Centered Review of Algorithms in Decision-Making in Higher Education](https://mlsanity.com/paper/2302.05839/) (2023)
- [Towards a Non-Ideal Methodological Framework for Responsible ML](https://mlsanity.com/paper/2401.11131/) (2024)

## Abstract (arXiv)

Caseworkers in the child welfare (CW) sector use predictive decision-making algorithms built on risk assessment (RA) data to guide and support CW decisions. Researchers have highlighted that RAs can contain biased signals which flatten CW case complexities and that the algorithms may benefit from incorporating contextually rich case narratives, i.e. - casenotes written by caseworkers. To investigate this hypothesized improvement, we quantitatively deconstructed two commonly used RAs from a United States CW agency. We trained classifier models to compare the predictive validity of RAs with and without casenote narratives and applied computational text analysis on casenotes to highlight topics uncovered in the casenotes. Our study finds that common risk metrics used to assess families and build CWS predictive risk models (PRMs) are unable to predict discharge outcomes for children who are not reunified with their birth parent(s). We also find that although casenotes cannot predict discharge outcomes, they contain contextual case signals. Given the lack of predictive validity of RA scores and casenotes, we propose moving beyond quantitative risk assessments for public sector algorithms and towards using contextual sources of information such as narratives to study public sociotechnical systems.