Towards a ‘smart’ cost–benefit tool: using machine learning to predict the costs of criminal justice policy interventions

Abstract

Background The Manning Cost–Benefit Tool (MCBT) was developed to assist criminal justice policymakers, policing organisations and crime prevention practitioners to assess the benefits of different interventions for reducing crime and to select those strategies that represent the greatest economic return on investment. Discussion A challenge with the MCBT and other cost–benefit tools is that users need to input, manually, a considerable amount of point-in-time data, a process that is time consuming, relies on subjective expert opinion, and introduces the potential for data-input error. In this paper, we present and discuss a conceptual model for a ‘smart’ MCBT that utilises machine learning techniques. Summary We argue that the Smart MCBT outlined in this paper will overcome the shortcomings of existing cost–benefit tools. It does this by reintegrating individual cost–benefit analysis (CBA) projects using a database system that securely stores and de-identifies project data, and redeploys it using a range of machine learning and data science techniques. In addition, the question of what works is respecified by the Smart MCBT tool as a data science pipeline, which serves to enhance CBA and reconfigure the policy making process in the paradigm of open data and data analytics.

Adoption of cognitive computing decision support system in the assessment of health-care policymaking

“…The examination for each option can be performed based on prior data using ML, DL and suggestions can be made using RE. Manning et al (2018) proposed an ML-based smart cost-benefit tool Policy adoption…”

The Threat of Offensive AI to Organizations

“…Some attacks require careful planning long before the attack campaign to ensure that all of the attacker's tools and resources are obtainable. ML-based cost benefit analysis tools, such as in [146], may be used to identify which tools should be developed and how the attack infrastructure should be laid out (e.g., C2 servers, staging areas, etc). It could also be used to help identify other organizations that can be used as beach heads [110].…”

Evaluation of a place‐based collective impact initiative through cross‐sectoral data linkage

“…The Queensland Department of Education would provide NAPLAN numeracy and literacy scores; and school attendance and suspensions/exclusions. Given our interest in economic analyses such as cost-benefit and cost-effectiveness, we also planned to ask participating schools and agencies to record cost data about their programmes using another tool developed for the G-PTSS, the Economic Support and Reporting Tool (ESRT; Manning et al, 2018). Since these cost data pertain to programmes not children, they would not have been part of the child-centric linked database, and hence, they are not listed in Table 1.…”

“…For instance, Rumble's Quest is not simply a computer game that gives children a voice and validly and reliably measures their social-emotional well-being, it is a comprehensive system which provides schools and agencies real-time aggregated summary reports of data designed to support data-driven decisions about priorities for action and the strategies with the best evidence. A second example is the ESRT app, described earlier (Manning et al, 2018), which provides a logical and user-friendly interface to support schools and community agencies to record details of the services they provide for children and families. Complementing Rumble's Quest, it is designed to assist schools and communities in: (1) setting priorities and plans; (2) identifying the most cost-effective way of achieving strategic objectives; (3) providing information on alternatives that have the lowest impact on external parties while maximising benefits to programme participants and their families; (4) providing evidence on return on investment; and (5) documenting the decision process.…”