Category: Cadet Projects

This research delves into the relationship between criminal recidivism and insider threat risk, particularly within the U.S. Army. The methodology employed in this research focused on machine learning techniques but now emphasizes Generalized Linear Models (GLMs), to analyze the data and identify predictors of recidivism, which we then relate to Insider Threat.

This paper presents a case prioritization system that utilizes a deep learning classification model trained on expert evaluated insider threat cases to label cases as “negligible”, “low”, “medium”, or “high” threat level. This classification model enables a partnership between machine and human that focuses human effort for the greatest impact.