• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.127-137
• /
• 2019

Recidivism prediction has been a subject of constant research by experts since the early 1970s. But it has become more important as committed crimes by recidivist steadily increase. Especially, in the 1990s, after the US and Canada adopted the 'Recidivism Risk Assessment Report' as a decisive criterion during trial and parole screening, research on recidivism prediction became more active. And in the same period, empirical studies on 'Recidivism Factors' were started even at Korea. Even though most recidivism prediction studies have so far focused on factors of recidivism or the accuracy of recidivism prediction, it is important to minimize the prediction misclassification cost, because recidivism prediction has an asymmetric error cost structure. In general, the cost of misrecognizing people who do not cause recidivism to cause recidivism is lower than the cost of incorrectly classifying people who would cause recidivism. Because the former increases only the additional monitoring costs, while the latter increases the amount of social, and economic costs. Therefore, in this paper, we propose an XGBoost(eXtream Gradient Boosting; XGB) based recidivism prediction model considering asymmetric error cost. In the first step of the model, XGB, being recognized as high performance ensemble method in the field of data mining, was applied. And the results of XGB were compared with various prediction models such as LOGIT(logistic regression analysis), DT(decision trees), ANN(artificial neural networks), and SVM(support vector machines). In the next step, the threshold is optimized to minimize the total misclassification cost, which is the weighted average of FNE(False Negative Error) and FPE(False Positive Error). To verify the usefulness of the model, the model was applied to a real recidivism prediction dataset. As a result, it was confirmed that the XGB model not only showed better prediction accuracy than other prediction models but also reduced the cost of misclassification most effectively.

• Korean Journal of Forensic Psychology
• /
• v.13 no.2
• /
• pp.99-119
• /
• 2022

Research on sex offense has shown that sex offenders are very heterogeneous. Sex offenders are heterogeneous in their probability of risk of recidivism. Some sex offenders are known to be much higher in their tendencies to reactivate than others. The study examined the predictive and explanatory power of static and dynamic risk factors in STATIC-99 and HAGSOR-Dynamic which have been used in Korean correctional facilities since 2014. STATIC-99 and HAGSOR-Dynamic showed moderate predictive accuracy for all crimes(AUC = .737, AUC = .597, respectively, ps < .001). However, when examining sex crime alone, only STATIC-99 predicted recidivism significantly(AUC = .743, p < .001). The incremental predictive power of HAGSOR-Dynamic was confirmed; the explanatory power of Model 2 comprising both static and dynamic risk factors were significant beyond Model 1 comprising only static factors(∆χ²= 12.721, p < .001), but this tendency was only applied to the model of all crimes. These findings were discussed with implications of practicing the sex offender assessment and treatment.

• Korean Journal of Culture and Social Issue
• /
• v.10 no.2
• /
• pp.39-77
• /
• 2004

This literature review introduced the concept of psychopathy which has never been defined academically in Korea. Also it is reviewed how this concept could be applied as latent factor of criminal behavior in the forensic settings. For this purpose, first of all, the periodical change of psychopathy definition was explored. Then it was investigated which determinants might develop psychopathy and what would be the behavioral characteristics of psychopaths. Finally, risk assessment tools measuring psychopathy were introduced and their predictive efficacy and applicability in Korean criminal justice system was discussed.