Search

Assessing regulatory compliance of personal financial advice is currently a complex manual process. In Australia, only 5%- 15% of advice documents are audited annually and 75% of these are found to be non-compliant(ASI 2018b). This paper describes a pilot with an Australian government regulation agency where Artificial Intelligence (AI) models based on techniques such natural language processing (NLP), machine learning and deep learning were developed to methodically characterise the regulatory risk status of personal financial advice documents. The solution provides traffic light rating of advice documents for various risk factors enabling comprehensive coverage of documents in the review and allowing rapid identification of documents that are at high risk of non-compliance with government regulations. This pilot serves as a case study of public-private partnership in developing AI systems for government and public sector., Comment: Presented at AAAI FSS-19: Artificial Intelligence in Government and Public Sector, Arlington, Virginia, USA

In large-scale emergencies social media has become a key source of information for public awareness, government authorities and relief agencies. However, the sheer volume of data and the low signal-to- noise ratio limit the effectiveness and the efficiency of using social media as an intelligence resource. We describe Australian Crisis Tracker (ACT), a tool designed for agencies responding to large- scale emergency events, to facilitate the understanding of critical information in Twitter. ACT was piloted by the Australian Red Cross (ARC) during the 2013-2014 Australian bushfires season. Video is available at: https://www.youtube.com/watch?v=Y-1rtNFqQbE

In this paper, we analyse the sustainability of social networks using STrust, our social trust model. The novelty of the model is that it introduces the concept of engagement trust and combines it with the popularity trust to derive the social trust of the community as well as of individual members in the community. This enables the recommender system to use these different types of trust to recommend different things to the community, and identify (and recommend) different roles. For example, it recommends mentors using the engagement trust and leaders using the popularity trust. We then show the utility of the model by analysing data from two types of social networks. We also study the sustainability of a community through our social trust model. We observe that a 5% drop in highly trusted members causes more than a 50% drop in social capital that, in turn, raises the question of sustainability of the community. We report our analysis and its results.