A Predictive Analytics-Based Decision Support System for Drug Courts
- PDF / 985,298 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 41 Downloads / 198 Views
A Predictive Analytics-Based Decision Support System for Drug Courts Hamed M. Zolbanin 1 & Dursun Delen 2 & Durand Crosby 3 & David Wright 3
# Springer Science+Business Media, LLC, part of Springer Nature 2019
Abstract This study employs predictive analytics to develop a decision support system for the prediction of recidivism in drug courts. Based on the input from subject matter experts, recidivism is defined as the violation of the treatment program requirements within three years after admission. We use two data processing methods to improve the accuracy of predictions: synthetic minority oversampling and survival data mining. The former creates a balanced data set and the latter boosts the model’s performance by adding several new, informative variables to the data set. After running several tree-based machine learning algorithms on the input data, random forest achieved the best performance (AUROC = 0.884, accuracy = 80.76%). Compared with the original data, oversampling and survival data mining increased AUROC by 0.068 and 0.018, respectively. Their combined contribution to AUROC was 0.088. We present a simplified version of decision rules and explain how the decision support system can be deployed. Therefore, this paper contributes to the analytics literature by illustrating how date/time variables - in applications where the response variable is defined as the occurrence of some event within a certain period - can be used in data management to improve the performance of predictive models and the resulting decision support systems. Keywords Predictive analytics . Survival data mining . Machine learning . Drug court
1 Introduction With the influx of data in various forms in recent years, analytics has been used by many organizations to make datadriven decisions and improve daily operations (LaValle et al. 2011). It is expected that this trend will continue, as prior research has tied organizations’ productivity and competitiveness to the extent they use data and analytics to drive their decisions (Brynjolfsson et al. 2011; Chae et al. 2014; Davenport and Harris 2007). The use of data to drive decisions has helped pioneering companies increase their productivity between 5 to 6% (McAfee and Brynjolfsson 2012). Not surprisingly, therefore, 83% of thousands of CIOs participating in a worldwide survey administered in 2011 by IBM * Hamed M. Zolbanin [email protected] 1
Department of MIS, Operations Management, and Decision Sciences, University of Dayton, Dayton, OH, USA
2
Spears School of Business, Oklahoma State University, Stillwater, OK, USA
3
Department of Mental Health and Substance Abuse Services, Oklahoma City, OK, USA
identified business intelligence and analytics as their top priority for achieving greater competitiveness (Holsapple et al. 2014), an investment that pays off $13.01 for every dollar spent (Nucleus Research 2014). A significant advantage of data-driven decision making for organizations is realized when analytics is used for decisions that repeat at large scales (Provost and Fawcett
Data Loading...
