Interpretable Machine Learning Approaches to Prediction of Chronic Homelessness

TL;DR

This paper presents a novel interpretable machine learning model, HIFIS-RNN-MLP, that accurately predicts chronic homelessness using shelter records, balancing high recall and precision, and providing insights into contributing factors.

Contribution

The study introduces a new predictive model that combines static and dynamic features for forecasting chronic homelessness with interpretability, improving trust and understanding.

Findings

Achieved a mean recall of 0.921 and precision of 0.651 across 10-fold cross validation.

Provided interpretability to explain individual predictions and population factors.

State-of-the-art performance in predicting chronic homelessness.

Abstract

We introduce a machine learning approach to predict chronic homelessness from de-identified client shelter records drawn from a commonly used Canadian homelessness management information system. Using a 30-day time step, a dataset for 6521 individuals was generated. Our model, HIFIS-RNN-MLP, incorporates both static and dynamic features of a client's history to forecast chronic homelessness 6 months into the client's future. The training method was fine-tuned to achieve a high F1-score, giving a desired balance between high recall and precision. Mean recall and precision across 10-fold cross validation were 0.921 and 0.651 respectively. An interpretability method was applied to explain individual predictions and gain insight into the overall factors contributing to chronic homelessness among the population studied. The model achieves state-of-the-art performance and improved stakeholder trust of what is usually a "black box" neural network model through interpretable AI.