Researchers at Purdue University are trying to make it easy for recently released criminals to reconnect in regular society.

Researchers at Purdue University Polytechnic Institute are using artificial intelligence (AI) to pinpoint behavioral flags that can trigger early intervention before the parolee recommits crime – known as recidivism. (Purdue University)

The transition from prison back to regular society

It is not easy for newly-released criminals to find a place and acceptance back in regular society. Disappointed and often helpless, these criminals slip back into their old lawless ways – a tendency known as “recidivism.”

Statistics from the U.S. Department of Justice indicate that over 80% of people in state prisons were arrested at least once in the nine years after their release. Significantly, more than 50% of those arrests happened within the first year itself.

“The major reason recidivism is so high is the parolees don’t feel like they belong in the community,” said Umit Karabiyik of Purdue. “They have a hard time, and they immediately go back to their old criminal habits. Their old criminal communities are very welcoming.”

Marcus Rogers (Professor) and Karabiyik (Assistant Professor) are researching AI-enabled tools that could help reduce recidivism rates in parolees. They are specialists in the fields of digital and cyber forensics.

How it works

Key to their objective is the identification of risky behaviors, stressful situations, and other behavioral and physiological factors that induce criminal tendencies.

Monitoring these red flags would be gadgets such as electronic bracelets worn by the person on their body. These bracelets collect important information such as stress levels and heart rates.

Smartphones are also used to collect data such as the person’s location, photos taken, and other relevant information.

AI models will then make sense of all this data at periodic intervals to detect early any signs of recidivism.

The models and monitoring systems are currently under development. In the first instance, the researchers will deploy their system on 125 out of 250 new parolees. These will form the “treatment group,” while the other 125 will be designated as a “control” group.

“The goal of the study is to identify opportunities for early intervention to better assist those individuals to integrate back into general society successfully,” said Marcus Rogers.

Related Story:      Global Agency to Use AI to Nab Doping Athletes