Beyond Eviction Prediction: Leveraging Local Spatiotemporal Public Records to Inform Action
This work addresses the practical application of predictive models for social good in housing assistance, though it is incremental in improving outreach efficiency.
The paper tackles the problem of using eviction risk predictions to effectively target outreach efforts for housing stability, showing that risk scores enable caseworkers to reach more eviction-prone properties compared to neighborhood-based or history-focused policies.
There has been considerable recent interest in scoring properties on the basis of eviction risk. The success of methods for eviction prediction is typically evaluated using different measures of predictive accuracy. However, the underlying goal of such prediction is to direct appropriate assistance to households that may be at greater risk so they remain stably housed. Thus, we must ask the question of how useful such predictions are in targeting outreach efforts - informing action. In this paper, we investigate this question using a novel dataset that matches information on properties, evictions, and owners. We perform an eviction prediction task to produce risk scores and then use these risk scores to plan targeted outreach policies. We show that the risk scores are, in fact, useful, enabling a theoretical team of caseworkers to reach more eviction-prone properties in the same amount of time, compared to outreach policies that are either neighborhood-based or focus on buildings with a recent history of evictions. We also discuss the importance of neighborhood and ownership features in both risk prediction and targeted outreach.