Award Abstract # 1939579
FAI: Building a Fair Recommender System for Foster Care Services within the Constraints of a Sociotechnical System

NSF Org: IIS
Division of Information & Intelligent Systems
Recipient: THE RESEARCH FOUNDATION FOR THE STATE UNIVERSITY OF NEW YORK
Initial Amendment Date: December 23, 2019
Latest Amendment Date: July 18, 2022
Award Number: 1939579
Award Instrument: Standard Grant
Program Manager: Todd Leen
tleen@nsf.gov
 (703)292-7215
IIS
 Division of Information & Intelligent Systems
CSE
 Directorate for Computer and Information Science and Engineering
Start Date: January 1, 2020
End Date: December 31, 2023 (Estimated)
Total Intended Award Amount: $452,631.00
Total Awarded Amount to Date: $468,631.00
Funds Obligated to Date: FY 2020 = $468,631.00
History of Investigator:
  • Kenneth Joseph (Principal Investigator)
    kjoseph@buffalo.edu
  • Atri Rudra (Co-Principal Investigator)
  • Huei-Yen Chen (Co-Principal Investigator)
  • Melanie Sage (Co-Principal Investigator)
  • Maria Rodriguez (Co-Principal Investigator)
  • Varun Chandola (Former Co-Principal Investigator)
Recipient Sponsored Research Office: SUNY at Buffalo
520 LEE ENTRANCE STE 211
AMHERST
NY  US  14228-2577
(716)645-2634
Sponsor Congressional District: 26
Primary Place of Performance: SUNY at Buffalo
520 Lee Entrance
Amherst
NY  US  14228-2567
Primary Place of Performance
Congressional District:
26
Unique Entity Identifier (UEI): LMCJKRFW5R81
Parent UEI: GMZUKXFDJMA9
NSF Program(s): Fairness in Artificial Intelli,
IIS Special Projects
Primary Program Source: 01002021DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 0757, 075Z, 9251
Program Element Code(s): 114Y00, 748400
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.070

ABSTRACT

There are more than 400,000 youth in foster care in the US, and each year more than 20,000 age out of foster care without reunifying with their families. The outcomes for these youth are poor. By age 19, only 59% finish high school, 20% have been homeless, and 27% of males have been incarcerated. These outcomes have significant and costly impacts for the youth and for society. Fortunately, youth in foster care are potentially eligible to receive services, such as vocational training, that may improve their chances at positive life outcomes. However, caseworkers are typically only able to identify youth for these services after the youth experiences a relevant need or crisis. To address this problem, this project will develop an algorithm to assist caseworkers in identifying youth in need of services before crises occur, and to allocate those services in a fair and just way. Critically, the algorithm will be informed at every step by inputs from foster youth and caseworkers. The methods developed will free resources for foster care agencies that are chronically underfunded and understaffed, increase procedural transparency and accountability in decision-making, and provide a critical tool to identify youth who need services before crises occur.

In developing the service recommendation algorithm, three fundamental research objectives will be addressed. First, methods will be developed to help domain experts identify and mitigate hard-to-find social biases in training data. Second, methods will be developed to identify multiple perspectives of fairness (e.g. from foster youth and case workers) with respect to service allocation decisions. Finally, a method will be developed to recommend service allocation strategies for foster youth in ways that balance the goal of ensuring fair distribution, according to multiple perspectives on fairness, and the goal of increasing the odds of positive life outcomes of all youth. All approaches will be evaluated extensively, with tight integration with multiple stakeholders in foster care. We will also provide evidence of the generality of our methods to other domains and provable bounds on their efficiency and accuracy. Stakeholder integration includes a partnership with a local foster care agency servicing over 10,000 youth per year, and a Youth Advisory Council of youth with experience in foster care who will play an important role in model development.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

(Showing: 1 - 10 of 15)
Dancy, Christopher L and Joseph, Kenneth "Computational Models for Social Good: Beyond Bias and Representation" SBP-BRiMs'22 , v.13558 , 2022 Citation Details
Du, Yuhao and Ionescu, Stefania and Sage, Melanie and Joseph, Kenneth "A Data-Driven Simulation of the New York State Foster Care System" FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency , 2022 https://doi.org/10.1145/3531146.3533165 Citation Details
Du, Yuhao and Nordell, Jessica and Joseph, Kenneth "Insidious Nonetheless: How Small Effects and Hierarchical Norms Create and Maintain Gender Disparities in Organizations" Socius: Sociological Research for a Dynamic World , v.8 , 2022 https://doi.org/10.1177/23780231221117888 Citation Details
Hall, Seventy F. and Sage, Melanie and Scott, Carol F. and Joseph, Kenneth "A Systematic Review of Sophisticated Predictive and Prescriptive Analytics in Child Welfare: Accuracy, Equity, and Bias" Child and Adolescent Social Work Journal , 2023 https://doi.org/10.1007/s10560-023-00931-2 Citation Details
Hannan, Jacqueline and Chen, Huei-Yen Winnie and Joseph, Kenneth "Who Gets What, According to Whom? An Analysis of Fairness Perceptions in Service Allocation" Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society , 2021 https://doi.org/10.1145/3461702.3462568 Citation Details
Ionescu, Stefania and Hannák, Anikó and Joseph, Kenneth "An Agent-based Model to Evaluate Interventions on Online Dating Platforms to Decrease Racial Homogamy" Conference on Fairness, Accountability, and Transparency (FAccT 21), , 2021 https://doi.org/10.1145/3442188.3445904 Citation Details
Joseph, Kenneth and Chen, Huei-Yen Winnie and Ionescu, Stefania and Du, Yuhao and Sankhe, Pranav and Hannak, Aniko and Rudra, Atri "A qualitative, network-centric method for modeling socio-technical systems, with applications to evaluating interventions on social media platforms to increase social equality" Applied Network Science , v.7 , 2022 https://doi.org/10.1007/s41109-022-00486-8 Citation Details
Joseph, Kenneth and Morgan, Jonathan "When do Word Embeddings Accurately Reflect Surveys on our Beliefs About People?" Association for Computational Linguistics , v.Proceed , 2020 https://doi.org/10.18653/v1/2020.acl-main.405 Citation Details
Radford, Jason and Joseph, Kenneth "Theory In, Theory Out: The Uses of Social Theory in Machine Learning for Social Science" Frontiers in Big Data , v.3 , 2020 https://doi.org/10.3389/fdata.2020.00018 Citation Details
Sankhe, Pranav and Hall, Seventy F. and Sage, Melanie and Rodriguez, Maria Y. and Chandola, Varun and Joseph, Kenneth "Mutual Information Scoring: Increasing Interpretability in Categorical Clustering Tasks with Applications to Child Welfare Data" SBP-BRiMS 2022 , v.13558 , 2022 Citation Details
Vergara, Jan_Voltaire and Rodriguez, Maria_Y and Phillips, Jonathan and Dohler, Ehren and Villodas, Melissa_L and Wilson, Amy_Blank and Joseph, Kenneth "An evaluation framework for predictive models of neighbourhood change with applications to predicting residential sales in Buffalo, NY" Urban Studies , v.61 , 2023 https://doi.org/10.1177/00420980231189403 Citation Details
(Showing: 1 - 10 of 15)

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.


Youth who age out of the American Foster Care System- that is, those who reach the age at which the system will no longer provide for them- are more likely than youth not in foster care to experience poor life outcomes. For example, nearly half of these youth will be homeless at some point in their life. This project aimed to develop computational tools, in tight collaboration with scholars from Human Factors Engineering and both scholars and practitioners in the field of Social Work, that were useful in helping us to understand why life outcomes for these youth are so poor and what can be done to improve these outcomes and make them more equitable.


Our work has also made significant contributions to intellectual merit in Social Work, Computer Science, and Human Factors Engineering. With respect to Social Work, we have introduced several new (to Social Work) methods to study decision-making and to expose biases in decisions that may lead to inequalities in youth outcomes, and to help explore possible interventions at both the level of the individual organization (e.g. through new user interfaces that help with collaborative decision-making) and at the level of the entire child welfare system (e.g. through the use of exploratory computer simulation models).  With respect to Computer Science, the unique constraints of providing services to older youth in care has led us to develop new problems and methods that help in our unique setting, but also turn out to be interesting from a theoretical perspective, and useful in the computational study of other areas of human services where equitable and effective allocation is necessary. Finally, with respect to Human Factors Engineering, we introduce a new sociotechnical domain for human factors to study naturalistic decision-making and human-automation (ML) collaboration in decision-making, and identify new ways to investigate the role of biases in how human decision makers interpret and use automated decision aids.  


With respect to broader impacts, our work has made progress in both moving towards a more promising and equitable future for older youth in care. At the national level, we have provided the community with the most comprehensive analysis yet of the factors that impact which youth receive services and what impacts outcomes for these youth, showing that 1) existing services have limited impacts or that existing data is not effective in estimating these effects, and 2) that service allocation patterns are likely driven primarily by state-level policy decisions. At the local level, we have worked with Hillside Agencies to improve the use of data-driven decision-making in the context of therapeutic foster care, and are helping them to build new user interfaces for this purpose.


The project supported the training of four Ph.D. students and twelve UG students (many of whom made fundamental contributions to the project, and nine of which are from Historically Under-represented Groups in Computer Science). 


 


Last Modified: 04/05/2024
Modified by: Kenneth Joseph

Please report errors in award information by writing to: awardsearch@nsf.gov.

Print this page

Back to Top of page