Homelessness prediction models in high-income countries: a scoping review
Bibliographic record
Abstract
Objective This scoping review aims to provide an overview of prediction models for future homelessness in high-income countries. Background Several risk prediction models for homelessness have been developed and are being used in practice. However, no comprehensive review has captured the full scope of these models in regard to their target populations, data and variables used, type of model, and model validation. Methods We searched MEDLINE, Web of Science, the Cochrane Library, and Bielefeld BASE without language or time restraints. Following the JBI guidelines, screening was performed by two independent reviewers; the data were extracted by one, of which 20% was checked by a second one. Studies that reported on the development or validation of prediction models for becoming homeless in high-income countries, and whose study population included individuals residing in these countries who were not homeless at the time of recruitment, were included. Results Our search resulted in 9,371 deduplicated records across databases. 15 studies met the inclusion criteria, of which 14 were model development studies and one was a validation study. 13 studies (87%) were conducted in the US, six of them in New York City (NYC). One study was conducted in Canada and one in Australia. Regarding the target population, three studies developed models for veterans and six studies targeted welfare applicants or recipients. One study focused on both youth emerging from public assistance and unemployed workers. Three studies developed models for the general population, while two were conducted in emergency departments. Of the 15 studies, 14 used traditional regression, seven employed other machine learning algorithms and six used both methods. The most common predictor types were: demographics, age, previous experiences of homelessness, human capital such as employment status or total debt and clinical variables such as physical or mental health status. Three studies combined geographical-level and individual-level data. In total, 25 models were identified, two of which were externally validated. Conclusions We found a broad spectrum of heterogeneity of models and population studies, an increase in model development over time, and limited use of calibration metrics. Prediction models for future homelessness have the potential to improve risk targeting and the effectiveness of preventive programs. As only two models were externally validated, we recommend that future research focuses on model evaluation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.033 | 0.157 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.008 | 0.013 |
| Bibliometrics | 0.017 | 0.016 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.006 | 0.006 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".