Abstract :

Crime Against Women Remains A Persistent Social, Legal, And Security Challenge Across Regions Worldwide [5], [6]. Traditional Crime Metrics Often Oversimplify The Multifaceted Nature Of Gender-based Violence, Resulting In Weak Predictive Insights And Incomplete Policy Recommendations [8], [12]. This Study Proposes A Hybrid Analytical Model Combining Machine Learning (ML) Classification Techniques With Regression-based Statistical Validation To Construct And Validate A Multidimensional Crime Index (MDCI), An Approach Aligned With Earlier Efforts To Fuse Spatial Analytics And ML For Crime Research [1], [3], [4]. The Model Integrates Diverse Socio-economic, Demographic, And Spatiotemporal Variables To More Accurately Reflect Crime Severity, Vulnerability, And Community-level Risk, Consistent With Prior Studies That Emphasize Contextual Risk Factors [7], [11], [13], [14]. Experimental Results Demonstrate That The Hybrid Framework Improves Prediction Accuracy, Robustness, And Interpretability When Compared With Standalone ML Or Regression Methods [2], [3]. The Proposed Index Shows Potential As A Decision-support Tool For Law Enforcement, Policymakers, And NGOs Focused On Women’s Safety [5], [9]. Keywords: Crime Against Women, Multidimensional Crime Index (MDCI), Machine Learning (ML), Regression Analysis, Hybrid Analytical Model, Gender-Based Violence, Predictive Crime Analytics,

Published:

29-11-2025

Issue:

Vol. 25 No. 11 (2025)

Page Nos:

273-279

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite