• Sirjan Kaur

This study employs TensorFlow Decision Forests, a machine learning framework, to analyze data from 2018 to 2021 and predict the prevalence of sexual violence against women aged 15-24 across 195 countries. Results reveal a high accuracy in predicting sexual abuse rates, with an F-score of 0.75, and highlight geographic variations, particularly in Central and West Africa. Additionally, an analysis of income inequality suggests a correlation with higher rates of sexual violence, while South Africa stands out as an outlier. Despite methodological limitations, such as underreporting biases, the research provides insights crucial for evidence-based policymaking and intervention strategies to combat this pervasive human rights issue. These findings hold promise for informing United Nations initiatives aimed at addressing sexual violence globally, facilitating resource allocation and targeted interventions to support survivors and prevent further instances of abuse.

Using Machine Learning to Estimate Sexual Violence Against Women aged 15-24 in Different Countries: A Comparative Analysis

"Using Machine Learning to Estimate Sexual Violence Against Women aged 15-24 in Different Countries: A Comparative Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 2, page no.f818-f822, February-2024, Available :http://www.jetir.org/papers/JETIR2402599.pdf

"Using Machine Learning to Estimate Sexual Violence Against Women aged 15-24 in Different Countries: A Comparative Analysis", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 2, page no. ppf818-f822, February-2024, Available at : http://www.jetir.org/papers/JETIR2402599.pdf