Analysis of Mexican Women’s Decision-Making Power Using Machine Learning Strategies

In Mexico, as in the rest of the world, there are different problems to solve regarding social analysis. One of them is gender violence, which primarily affects women. Thanks to the development of technology and algorithms based on artificial intelligence, it is possible to use techniques capable of determining situations of violence. This article uses two of these algorithms to classify Mexican women’s decision-making power in the home. The methodology employed included the ENDIREH 2016 database, with 29,708 records. Experiments were conducted employing Random Forest and k-Nearest Neighbors algorithms. The results suggest no statistical difference between the methods with a p=0.741 Student’s t-test value. Both algorithms obtained 99% in terms of accuracy, sensitivity, and specificity and a false-positive ratio of 0.31% and 0.33%, respectively.