Search

AIM To quantify the effects of individual liquor licensing policies introduced in New South Wales (NSW) over the last decade on rates of violent crime. METHOD The effects of individual state-wide policies on non-domestic assaults in NSW and additional local policies in the Sydney Central Business District Entertainment Precinct (CBD) and the Kings Cross Entertainment Precinct (KCP) from 2000 to 2019 were quantified using time series intervention models. We used a vector auto regression (VAR) model to create counterfactual datasets. These datasets were derived from proxy data outside the study area and helped predict potential assault outcomes without the policy implementation. RESULTS The liquor licensing policies introduced by the NSW Government between 2008 and 2018 contributed to a significant decline in non-domestic assaults, both in Sydney and across NSW. By the end of 2019, non-domestic assaults had reduced by an estimated 19% in NSW, 45% in the Sydney CBD, and 84% in the KCP. Policies restricting late night (or 24-hour) trading of licensed premises and those targeting enforcement toward the highest risk venues contributed most to these declines. CONCLUSION This research adds to the mounting evidence that restricting trading hours can substantially reduce the risks associated with acute alcohol intoxication and can be a cost-effective crime reduction strategy when combined with enforcement that targets the small number of premises that account for most of the harm. [ABSTRACT FROM AUTHOR]

The use of artificial intelligence for decision support and automation has shown tremendous potential in many areas. The ability to explain the decisions made by a machine learning algorithm is fundamental to facilitating the widespread use of this type of tool. There are many important real-world problems where the cost of the decisions depends on the characteristics of each example: these are called example-dependent cost (EDC) problems. For this type of classification problem, an appropriate formulation that takes into account the decision costs is fundamental both for the design of the classifier and for the explanation of its decisions. In this paper, we propose COCOA, an explanation method designed for EDC problems based on a Bayesian discriminant. The proposed method can provide counterfactual samples generated by considering decision costs. The COCOA method provides valid and plausible counterfactuals with a high success rate, which can be actionable, diverse, and sparse, achieving a remarkable improvement in terms of cost over five state-of-the-art methods on six real-world datasets. • COCOA provides actionable, plausible, sparse and diverse counterfactuals. • Decision costs are taken into account when generating counterfactuals. • The obtained counterfactuals improve cost savings. • The method is presented for MLPs, but other architectures can be used. [ABSTRACT FROM AUTHOR]

Abstract: In this note, we address the problem of surrogacy using a causal modelling framework that differs substantially from the potential outcomes model that pervades the biostatistical literature. The framework comes from econometrics, and it conceptualizes direct effects of the surrogate endpoint on the true endpoint. While this framework can incorporate the so-called semi-competing risks data structure, we also derive a fundamental non-identifiability result. Relationships to existing causal modelling frameworks are also discussed. [Copyright &y& Elsevier]