Search
Browse By Day
Browse By Time
Browse By Person
Browse By Area
Browse By Session Type
Search Tips
ASC Home
Sign In
X (Twitter)
The authors used deep neural networks to predict recidivism for individuals released under parole in Georgia. After predicting recidivism across a 3-year period, the neural network approach was recognized in the competition for its accuracy in predicting recidivism for female releasees. This lightning talk will discuss the promising potential and drawbacks to using machine learning techniques to predict risk for recidivating, particularly for specific groups such as women.