Machine Learning Based Approach for Crime Analysis in India with an Emphasis on Women Safety

Analyze India’s historical crime statistics, with an emphasis on crimes against women. Engage communities, evaluate model performance, and propose evidence-based policies with ethical considerations for crime prevention. This study employs machine learning to proactively address women’s safety concerns in India, enabling data-driven decision-making, targeted resource allocation, community empowerment, technology integration, and ethical considerations for comprehensive crime analysis and policy recommendations. This study employed supervised machine learning techniques, as Logistic Regression, SVM, Random Forest, K-Neighbors Classifier, Decision Tree Classifier, Gaussian NB, XGB Classifier, Gradient Boosting Classifier, LGBM algorithms, to predict crime occurrences. The machine learning model successfully predicted crime hotspots, indicating its potential for proactive crime prevention, aiding law enforcement in targeted resource allocation. The study’s results form a robust foundation for evidence-based policy recommendations, emphasizing the need for tailored interventions to enhance women’s safety in diverse Indian communities. The proposal works on India’s crime and crime against women dataset and the data collection indicates the increasing or decreasing the crime record. In summary, the study’s significance lies in its holistic approach to leveraging machine learning for crime analysis with a specific focus on women’s safety, ultimately aiming to create safer communities and contribute to the overall well-being of the population.