Abstract
The analysis of gender-based violence in higher education institutions is crucial due to its impact on safety, psychological well-being, and academic performance of affected individuals. This study aims to diagnose the climate of violence in these institutions using Machine Learning techniques. Data were collected from students, teachers, and administrative staff through a questionnaire that assessed perceptions of safety, experiences of physical, verbal, psychological, and sexual violence, as well as the effectiveness of institutional measures. With a sample of 1,100 records, models such as Dense Neural Networks (DNN), Recurrent Neural Networks (LSTM), and Convolutional Neural Networks (CNN) were applied, following the functional data science methodology in eight out of ten stages. The data were processed and divided into training and testing sets, with features normalized to optimize performance. Among the evaluated models, the CNN stood out by achieving 100% sensitivity, identifying all cases without omissions, while the DNN and LSTM achieved sensitivity of 99.53%, with precisions of 99.07% and 98.17%, respectively. This innovative approach highlights the effectiveness of Machine Learning for monitoring and preventing violence, providing robust tools for decision-making and promoting the implementation of inclusive and effective policies in educational institutions.