ABSTRACT:

Using novel 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 it uses data currently available to them. 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. Full paper can be found at https://arxiv.org/abs/2011.12057

BIO:

Anna Zhu is a lecturer of economics at RMIT University. Her research aims to identify how social policy can enable economically disadvantaged persons towards greater participation in society and well-being. She is currently leading an Australian Research Council Linkage grant on the intergenerational impacts of welfare reform. Most recently, she has applied machine learning techniques to novel administrative data in order to predict those who are at risk of long-term welfare receipt. Her personal website is: https://annazhu.site/