Using Machine Learning to Create an Early Warning System for Welfare Recipients

TL;DR

This paper develops machine learning models using nationwide social security data to accurately predict income support receipt durations, offering a cost-effective tool for early intervention and welfare cost savings.

Contribution

It introduces the first application of machine learning for predicting income support duration using comprehensive administrative data in Australia, outperforming existing heuristic methods.

Findings

Machine learning models improve prediction accuracy by at least 22%.

The models use existing administrative data at no extra cost.

Enhanced detection of long-term welfare recipients can lead to significant savings.

Abstract

Using high-quality nation-wide social security data combined with machine learning tools, we develop predictive models of income support receipt intensities for any payment enrolee in the Australian social security system between 2014 and 2018. We show that off-the-shelf machine learning algorithms can significantly improve predictive accuracy compared to simpler heuristic models or early warning systems currently in use. Specifically, the former predicts the proportion of time individuals are on income support in the subsequent four years with greater accuracy, by a magnitude of at least 22% (14 percentage points increase in the R2), compared to the latter. This gain can be achieved at no extra cost to practitioners since the algorithms use administrative data currently available to caseworkers. Consequently, our machine learning algorithms can improve the detection of long-term income support recipients, which can potentially provide governments with large savings in accrued welfare costs.