Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enhancing Equitable Access to AI in Housing and Homelessness System of Care through Federated Learning

Musa Taib, Jiajun Wu, Steve Drew, Geoffrey G. Messier

TL;DR

This study addresses the challenge of equitably deploying predictive analytics across a fragmented Housing and Homelessness System of Care (HHSC) while preserving privacy. It introduces a Federated Learning (FL) framework, built on FedAvg, to train a common model for forecasting chronic/episodic shelter use from shelter-sleep data without sharing identifying records. Using real-world Calgary data, the authors compare Centralized, Federated, and Isolated deployment modes, showing that FL achieves performance within ~4% of the fully centralized approach and yields notable gains for smaller agencies, thereby promoting data equity. The results demonstrate the practical viability of FL to enable privacy-preserving, cross-agency AI support for frontline staff, reducing data-linkage needs and enhancing equitable access to high-quality predictive tools in social services.

Abstract

The top priority of a Housing and Homelessness System of Care (HHSC) is to connect people experiencing homelessness to supportive housing. An HHSC typically consists of many agencies serving the same population. Information technology platforms differ in type and quality between agencies, so their data are usually isolated from one agency to another. Larger agencies may have sufficient data to train and test artificial intelligence (AI) tools but smaller agencies typically do not. To address this gap, we introduce a Federated Learning (FL) approach enabling all agencies to train a predictive model collaboratively without sharing their sensitive data. We demonstrate how FL can be used within an HHSC to provide all agencies equitable access to quality AI and further assist human decision-makers in the allocation of resources within HHSC. This is achieved while preserving the privacy of the people within the data by not sharing identifying information between agencies without their consent. Our experimental results using real-world HHSC data from Calgary, Alberta, demonstrate that our FL approach offers comparable performance with the idealized scenario of training the predictive model with data fully shared and linked between agencies.

Enhancing Equitable Access to AI in Housing and Homelessness System of Care through Federated Learning

TL;DR

This study addresses the challenge of equitably deploying predictive analytics across a fragmented Housing and Homelessness System of Care (HHSC) while preserving privacy. It introduces a Federated Learning (FL) framework, built on FedAvg, to train a common model for forecasting chronic/episodic shelter use from shelter-sleep data without sharing identifying records. Using real-world Calgary data, the authors compare Centralized, Federated, and Isolated deployment modes, showing that FL achieves performance within ~4% of the fully centralized approach and yields notable gains for smaller agencies, thereby promoting data equity. The results demonstrate the practical viability of FL to enable privacy-preserving, cross-agency AI support for frontline staff, reducing data-linkage needs and enhancing equitable access to high-quality predictive tools in social services.

Abstract

The top priority of a Housing and Homelessness System of Care (HHSC) is to connect people experiencing homelessness to supportive housing. An HHSC typically consists of many agencies serving the same population. Information technology platforms differ in type and quality between agencies, so their data are usually isolated from one agency to another. Larger agencies may have sufficient data to train and test artificial intelligence (AI) tools but smaller agencies typically do not. To address this gap, we introduce a Federated Learning (FL) approach enabling all agencies to train a predictive model collaboratively without sharing their sensitive data. We demonstrate how FL can be used within an HHSC to provide all agencies equitable access to quality AI and further assist human decision-makers in the allocation of resources within HHSC. This is achieved while preserving the privacy of the people within the data by not sharing identifying information between agencies without their consent. Our experimental results using real-world HHSC data from Calgary, Alberta, demonstrate that our FL approach offers comparable performance with the idealized scenario of training the predictive model with data fully shared and linked between agencies.
Paper Structure (23 sections, 3 figures, 4 tables, 3 algorithms)

This paper contains 23 sections, 3 figures, 4 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Homelessness Prediction
  4. Federated Learning
  5. FL for Risk Prediction
  6. Dataset
  7. Data Preprocessing
  8. Labeling
  9. Methodology
  10. Problem Formulation
  11. Training Details
  12. Evaluation
  13. Experimental Setup
  14. Train/Test Splits
  15. Machine Learning Models
  16. ...and 8 more sections

Figures (3)

  • Figure 1: (Total Episode, Total Stay) clusters identifying transitional, chronic and episodic shelter use.
  • Figure 2: Illustration of the three scenarios for training predictive models in the paper: Federated, Centralized, and Isolated.
  • Figure 3: F1 Scores for Federated and Isolated cases