Intelligent Parole violation Predication Using Neural Network

This project presented an Intelligent Parole Violation Prediction System that leverages Artificial Intelligence .and Machine Learning techniques to support data-driven and unbiased parole decision-making. By utilizing a neural network model trained on historical parole data, the system effectively analyses multiple offender- related factors, including demographics, criminal history, offense characteristics, and supervision details, to predict the likelihood of parole violations. This approach addresses the limitations of traditional parole assessment methods that rely heavily on subjective judgment and incomplete information.

[1]. An Algorithmic Assessment of Parole Decisions — Authors: Hannah S. Laqueur & Ryan W. Copus — Journal: Journal of Quantitative Criminology — DOI: 10.1007/s10940-022-09563-8 — E-ISSN: 1573-7799. [2]. A Multi‑Layer Perceptron (MLP) Neural Networks for Stellar Classification: A Review of Methods and Results — Authors: Tamer Soliman & Ayman H. Abd‑elaziem — International Journal of Advances in Applied Computational Intelligence (IJAACI) Vol. 03 No. 02 (2023), pp. 29-37; DOI: 10.54216/IJAACI.030203 [3]. An Impact Assessment of Machine Learning Risk Forecasts on Parole Board Decisions and Recidivism, by Richard Berk, published in the Journal of Experimental Criminology, Vol. 13, Issue 2, June 2017, pp. 193–216 (NCJ 251969). [4]. Machine Learning and Criminal Justice: A Systematic Review of Advanced Methodology for Recidivism Risk Prediction — Authors: Guido Vittorio Travaini, Federico Pacchioni, Silvia Bellumore, Marta Bosia, and Francesco De Micco — Journal:*Journal of Clinical Medicin, Published by MDPI .