ATO Debt Collection Optimisation

Project Member(s): Cao, L.

Funding or Partner Organisation: Australian Taxation Office

Start year: 2013

Summary: The Debt Strategic Research and Analysis team has been working with the Advanced Analytics Institute at the University of Technology, Sydney (UTS) on the Debt Collection Optimisation using Advanced Analytics Project. The aim of this project is to improve workforce resource productivity by targeted streaming of debt cases to the most appropriate collection actions. The current contract with the UTS (12.181) expires on 20 June 2013 and addresses Phase 1 of the overarching plan and is being undertaken to support shifting actions from low-risk taxpayers to high-risk taxpayers through identification of debts which are likely to be paid in full, within a certain timeframe, and therefore do not require action by the ATO. This contract will assist the project to mine for ICP debt cases and/or clients which are likely to selffinalise without needing any treatment action(s). Appropriate algorithms will be generated to identify and predict such cases. It will also assist to improve workforce resource productivity by targeted streaming of debt cases to the most appropriate collection actions. The Service for the Debt Collection Optimisation using the Advanced Analytics project, forms part of the UTS-ATO research partnership Effective Profiling and Detection of at-Risk Taxpayers to Strengthen ATO Compliance.

Keywords: Explore data, deeper understanding of debt distribution, across segments, their relationship with debt finalisation, payment period/level and client profiles,key discriminative factors that differentiate the self finaliser,cases from non-self finaliser cases, build models to predict the self finaliser likelihood of new debt cases,relationship between debt cases/clients and treatment actions under different scenarios, Identify most cost-effective or the most ineffective action(s) for each case, Optimise case-action matching for the greatest impact and resource efficiency, Maximise the dollar value of collected debt with given resources with implications for FTE workforce allocation

FOR Codes: Pattern Recognition and Data Mining, Simulation and Modelling, Information Processing Services (incl. Data Entry and Capture), Modelling and simulation, Knowledge representation and reasoning, Information systems, technologies and services not elsewhere classified

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.