| Resumen |
Gender-based violence is a pervasive issue, particularly in Mexico City, where alarming statistics underscore the urgent need for effective interventions. This research proposes a methodology integrating machine learning and geospatial analysis to analyze violent acts against women. Various machine learning models are implemented to classify gender crimes, while geospatial analysis visualizes crime patterns. The results show that machine learning effectively predicts and categorizes gender-based crimes, with SVM performing exceptionally well. Geospatial analysis reveals concentration areas of gender-based violence, informing targeted interventions. This study contributes to understanding gender-based violence dynamics and guides evidence-based policy-making efforts. Future research should focus on refining predictive models and addressing data quality challenges. Ultimately, the synergy between technology and interdisciplinary approaches holds promise for advancing interventions against gender-based violence. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. |
