Despite all the promises of analytics, its complexity, multidimensionality, and multidisciplinary nature can sometimes disserve its efficacy. What can further aggravate the problem is the need to deal with human behavior and social interactions as inherent qualities of the application domain. One such area is the drug court; an alternative for traditional criminal courts that attempts to transform the traditional punitive jurisprudence to a therapeutic one. Under this new philosophy, the eligible offenders are considered as individuals in need of rehabilitative treatments and are persuaded to undergo a regimen that seeks to return them back to the community, rather than sending them to prison. This initiative, if performed properly, has proven to be effective in lowering the costs and improving the social outcomes. While many researchers have studied this initiative from the perspective of its factors, requirements, and tradeoffs, there currently is a lack of a comprehensive analytics model that can accurately predict who would (or would not) graduate from these programs. To fill this gap, and to enable better management of resources and improvement of outcomes, this study develops an analytics model to describe a large real-world sample of drug court participants; to predict who would or would not graduate from these courts; and to prescribe a set of guidelines (presented as characteristics of the offenders) that can help jurisdictions and drug court administrators to make more effective and efficient decisions.
Read full abstract