Allocating Interventions Based on Predicted Outcomes: A Case Study on Homelessness Services

Modern statistical and machine learning methods are increasingly capable of modeling individual or personalized treatment effects. These predictions could be used to allocate different interventions across populations based on individual characteristics. In many domains, like social services, the availability of different possible interventions can be severely resource limited. This paper considers possible improvements to the allocation of such services in the context of homelessness service provision in a major metropolitan area. Using data from the homeless system, we use a counterfactual approach to show potential for substantial benefits in terms of reducing the number of families who experience repeat episodes of homelessness by choosing optimal allocations (based on predicted outcomes) to a fixed number of beds in different types of homelessness service facilities. Such changes in the allocation mechanism would not be without tradeoffs, however; a significant fraction of households are predicted to have a higher probability of re-entry in the optimal allocation than in the original one. We discuss the efficiency, equity and fairness issues that arise and consider potential implications for policy.

[1]  Mohammad Akbarpour,et al.  Thickness and Information in Dynamic Matching Markets , 2018, Journal of Political Economy.

[2]  Suresh Venkatasubramanian,et al.  Runaway Feedback Loops in Predictive Policing , 2017, FAT.

[3]  Marybeth Shinn,et al.  Efficient targeting of homelessness prevention services for families. , 2013, American journal of public health.

[4]  J. Kleinberg,et al.  Prediction Policy Problems. , 2015, The American economic review.

[5]  Jennifer L. Hill,et al.  Bayesian Nonparametric Modeling for Causal Inference , 2011 .

[6]  Milind Tambe,et al.  Optimal Allocation of Police Patrol Resources Using a Continuous-Time Crime Model , 2016, GameSec.

[7]  Sanmay Das,et al.  Risk and Risk Management in the Credit Card Industry , 2015 .

[8]  Jon M. Kleinberg,et al.  On Fairness and Calibration , 2017, NIPS.

[9]  Eric Rice,et al.  Designing Fair, Efficient, and Interpretable Policies for Prioritizing Homeless Youth for Housing Resources , 2018, CPAIOR.

[10]  Jill Khadduri,et al.  Costs Associated with First-Time Homelessness for Families and Individuals , 2010 .

[11]  Milind Tambe,et al.  Staying Ahead of the Game: Adaptive Robust Optimization for Dynamic Allocation of Threat Screening Resources , 2017, IJCAI.

[12]  Tony Doyle,et al.  Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy , 2017, Inf. Soc..

[13]  P. Hovmand,et al.  Capability Traps Impeding Homeless Services: A Community-Based System Dynamics Evaluation , 2019, Journal of social service research.

[14]  Uri Shalit,et al.  Learning Representations for Counterfactual Inference , 2016, ICML.

[15]  V. Crawford,et al.  An Invitation to Market Design , 2017 .

[16]  Andrés Carrión,et al.  Reliability and validity of the Vulnerability Index-Service Prioritization Decision Assistance Tool (VI-SPDAT) in real-world implementation , 2018, Journal of Social Distress and the Homeless.

[17]  H. Chipman,et al.  BART: Bayesian Additive Regression Trees , 2008, 0806.3286.

[18]  S. Metraux,et al.  THE PATTERNS AND COSTS OF SERVICES USE AMONG HOMELESS FAMILIES , 2011 .

[19]  Edward I. George,et al.  Bayesian Ensemble Learning , 2006, NIPS.

[20]  Avi Feller,et al.  Algorithmic Decision Making and the Cost of Fairness , 2017, KDD.

[21]  Elliot Anshelevich,et al.  On the Social Welfare of Mechanisms for Repeated Batch Matching , 2012, AAAI.

[22]  D. Culhane,et al.  The 2012 Annual Homelessness Assessment Report (AHAR) to Congress: Volume 2, Estimates of Homelessness in the United States , 2013 .