The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
AI and Juvenile Justice: Can Machine Learning Predict and Prevent Youth Crimes?
|
|
Author(s): Vivek Bhardwaj (School of Computer Science and Engineering, Manipal University Jaipur, India), Bilal Ahmed (School of Computer Application, Lovely Professional University, Phagwara, India), Mirza Shuja (School of Computer Application, Lovely Professional University, Phagwara, India), Deepak Thakur (Chitkara University Institute of Engineering and Technology, Chitkara University, India), Tanya Gera (Chitkara University Institute of Engineering and Technology, Chitkara University, India)and Mukesh Kumar (Advanced Centre of Research and Innovation, Department of Computer Application, Chandigarh School of Business, Chandigarh Group of Colleges Jhanjeri, Mohali, India)
Copyright: 2026
Pages: 26
Source title:
Child Protection Laws and Crime in the Digital Era
Source Author(s)/Editor(s): Romil Rawat (LabGeoInf-Research LABoratory in GEOmatics and INFormation systems, National Research Council in Italy, Rome, Italy), Sanjaya Kumar Sarangi (Utkal University, India), A. Samson Arun Raj (Karunya Institute of Technology and Sciences, India), Janet Olivia Richmond (Karunya Institute of Technology and Sciences, India)and Purvee Bhardwaj (Rabindranath Tagore University, India)
DOI: 10.4018/979-8-3373-5132-2.ch001
Purchase
|
Abstract
The integration of artificial intelligence (AI) into juvenile justice systems offers new avenues for early intervention and crime prevention. This study explores the potential of machine learning (ML) to predict juvenile offenses in India using socio-demographic and historical data. Drawing from over 1.2 million records (2010–2024) from the National Crime Records Bureau (NCRB), a hybrid ML approach was applied. The Extreme Gradient Boosting (XGBoost) model, effective in handling imbalanced data, was used to identify at-risk youth based on 15 features such as age, education, income, and type of first offense. The model achieved strong results—F1-score of 0.87, precision of 0.91, and recall of 0.83—surpassing traditional models. SHAP analysis highlighted key predictors like school dropout, urban-rural divide, and family crime history. Validated on 2024 data from Maharashtra, West Bengal, and Uttar Pradesh, the model reached 89.4% accuracy. The research supports AI-driven risk assessment tools to aid policy and resource planning in juvenile justice.
Related Content
|
Vivek Bhardwaj, Bilal Ahmed, Mirza Shuja, Deepak Thakur, Tanya Gera, Mukesh Kumar.
© 2026.
26 pages.
|
|
Vivek Bhardwaj, Tanima Thakur, Mrinalini Rana, Jeyaganesh Viswanathan.
© 2026.
24 pages.
|
|
Abhishek Sharma, Abhishek Mishra, Shweta Jain, Khushboo Karodiya, Priyanka Sharma.
© 2026.
10 pages.
|
|
Akash Mishra, Nandini Bansod, Dinesh Baban Kamble.
© 2026.
18 pages.
|
|
Anjali Rawat, George Kurian, Romil Rawat, Janet Olivia Richmond, Anand Rajavat, Purvee Bhardwaj.
© 2026.
28 pages.
|
|
Antonio Gonzalez-Torres.
© 2026.
26 pages.
|
|
Anjali Rawat, A. Samson Arun Raj, Janet Olivia Richmond, Anand Rajavat, Antonio González-Torres, Purvee Bhardwaj.
© 2026.
22 pages.
|
|
|