<p>Crime scene analysis requires the evaluation of multiple factors to determine a suspect’s guilt, a process that can be lengthy and costly. The integration of Artificial Intelligence (AI) into the judicial system is emerging as an opportunity to improve the efficiency of investigations and legal decision-making. In this study, we propose a Machine Learning (ML)-based methodology to support the assessment of road homicide cases under Italian law. Our approach employs a Large Language Model (LLM) to extract 51 features from crime scene descriptions automatically. Four ML models are then analyzed: <Emphasis FontCategory="NonProportional">Random Forest</Emphasis> (RF), <Emphasis FontCategory="NonProportional">Gradient Boosting Machine</Emphasis> (GBM), <Emphasis FontCategory="NonProportional">Decision Tree</Emphasis> (DT), and <Emphasis FontCategory="NonProportional">Logistic Regression</Emphasis> (LR). We evaluated the performance of these models on a dataset of 100 road homicide court rulings in Italy, achieving 95% accuracy in crime classification. The validation was conducted by comparing the model outputs with a legal ranking established by four legal experts, allowing us to verify the consistency of the algorithmic predictions with human legal reasoning. The results indicate that the <Emphasis FontCategory="NonProportional">Gradient Boosting Machine</Emphasis> shows the highest correlation with legal evaluations (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">$\rho = 0.857$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi>ρ</mi> <mo>=</mo> <mn>0.857</mn> </mrow> </math></EquationSource> </InlineEquation>, <InlineEquation ID="IEq2"> <EquationSource Format="TEX">$\tau = 0.714$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mi>τ</mi> <mo>=</mo> <mn>0.714</mn> </mrow> </math></EquationSource> </InlineEquation>, <i>p</i> values <InlineEquation ID="IEq3"> <EquationSource Format="TEX">$< 0.05$</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mo><</mo> <mn>0.05</mn> </mrow> </math></EquationSource> </InlineEquation>), while <Emphasis FontCategory="NonProportional">Logistic Regression</Emphasis> performed the worst. This study highlights the potential of AI in legal decision support, emphasizing the need to ensure transparency and bias mitigation to comply with European Union Regulations while maintaining human judgment as the central authority in legal proceedings.</p>

Machine learning in legal decision-making: analysis of judicial and algorithmic reasoning in road homicide cases

期刊论文
出版模式：

开放获取
发表日期：

2026年3月9日

查看全文

Grazia Garzo,
Alessandro Palumbo,
Mario Giampaolo

摘要

Crime scene analysis requires the evaluation of multiple factors to determine a suspect’s guilt, a process that can be lengthy and costly. The integration of Artificial Intelligence (AI) into the judicial system is emerging as an opportunity to improve the efficiency of investigations and legal decision-making. In this study, we propose a Machine Learning (ML)-based methodology to support the assessment of road homicide cases under Italian law. Our approach employs a Large Language Model (LLM) to extract 51 features from crime scene descriptions automatically. Four ML models are then analyzed: Random Forest (RF), Gradient Boosting Machine (GBM), Decision Tree (DT), and Logistic Regression (LR). We evaluated the performance of these models on a dataset of 100 road homicide court rulings in Italy, achieving 95% accuracy in crime classification. The validation was conducted by comparing the model outputs with a legal ranking established by four legal experts, allowing us to verify the consistency of the algorithmic predictions with human legal reasoning. The results indicate that the Gradient Boosting Machine shows the highest correlation with legal evaluations ( $\rho = 0.857$ $ρ = 0.857$ , $\tau = 0.714$ $τ = 0.714$ , p values $< 0.05$ $< 0.05$ ), while Logistic Regression performed the worst. This study highlights the potential of AI in legal decision support, emphasizing the need to ensure transparency and bias mitigation to comply with European Union Regulations while maintaining human judgment as the central authority in legal proceedings.