Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Human-Centered Review of Algorithms in Homelessness Research

Erina Seh-Young Moon, Shion Guha

TL;DR

This paper surveys how data-driven algorithms are designed for homelessness and evaluates them through a human-centered algorithm design lens. Analyzing 57 papers published from 1998 to 2023, it finds that fairness and bias are rarely examined and that most work emphasizes predictive risk of homelessness or related harms, often neglecting what services are actually available or needed. Resource allocation models frequently rely on simulations, raising concerns about external validity and real-world applicability. The authors advocate a shift toward data-centric AI and participatory, strength-based design, offering heuristic guidelines to center stakeholders, improve validity, and challenge the status quo in homelessness research.

Abstract

Homelessness is a humanitarian challenge affecting an estimated 1.6 billion people worldwide. In the face of rising homeless populations in developed nations and a strain on social services, government agencies are increasingly adopting data-driven models to determine one's risk of experiencing homelessness and assigning scarce resources to those in need. We conducted a systematic literature review of 57 papers to understand the evolution of these decision-making algorithms. We investigated trends in computational methods, predictor variables, and target outcomes used to develop the models using a human-centered lens and found that only 9 papers (15.7%) investigated model fairness and bias. We uncovered tensions between explainability and ecological validity wherein predictive risk models (53.4%) focused on reductive explainability while resource allocation models (25.9%) were dependent on unrealistic assumptions and simulated data that are not useful in practice. Further, we discuss research challenges and opportunities for developing human-centered algorithms in this area.

A Human-Centered Review of Algorithms in Homelessness Research

TL;DR

This paper surveys how data-driven algorithms are designed for homelessness and evaluates them through a human-centered algorithm design lens. Analyzing 57 papers published from 1998 to 2023, it finds that fairness and bias are rarely examined and that most work emphasizes predictive risk of homelessness or related harms, often neglecting what services are actually available or needed. Resource allocation models frequently rely on simulations, raising concerns about external validity and real-world applicability. The authors advocate a shift toward data-centric AI and participatory, strength-based design, offering heuristic guidelines to center stakeholders, improve validity, and challenge the status quo in homelessness research.

Abstract

Homelessness is a humanitarian challenge affecting an estimated 1.6 billion people worldwide. In the face of rising homeless populations in developed nations and a strain on social services, government agencies are increasingly adopting data-driven models to determine one's risk of experiencing homelessness and assigning scarce resources to those in need. We conducted a systematic literature review of 57 papers to understand the evolution of these decision-making algorithms. We investigated trends in computational methods, predictor variables, and target outcomes used to develop the models using a human-centered lens and found that only 9 papers (15.7%) investigated model fairness and bias. We uncovered tensions between explainability and ecological validity wherein predictive risk models (53.4%) focused on reductive explainability while resource allocation models (25.9%) were dependent on unrealistic assumptions and simulated data that are not useful in practice. Further, we discuss research challenges and opportunities for developing human-centered algorithms in this area.
Paper Structure (32 sections, 4 figures, 5 tables)

This paper contains 32 sections, 4 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Research Context
  4. Methods
  5. Scoping criteria and data collection process
  6. Data analysis
  7. Results
  8. Dataset Characterstics
  9. Computational Methods Employed in Algorithms for Homelessness (RQ1)
  10. Inferential Statistics
  11. Machine Learning (ML) and Deep Learning (DL) Methods
  12. Optimization Techniques
  13. Predictors Deployed in Algorithms for Homelessness
  14. Predictors about demographics and health-related variables
  15. Predictors about housing and services
  16. ...and 17 more sections

Figures (4)

  • Figure 1: The methods used to build algorithms
  • Figure 2: The predictors used in the algorithms
  • Figure 3: Outcome variables for the algorithms
  • Figure 4: Flow diagram of the literature review process