Framework for Bias Detection in Machine Learning Models: A Fairness Approach

The research addresses bias and inequity in binary classification problems in machine learning. Despite existing ethical frameworks for artificial intelligence, detailed guidance on practices and techniques to address these issues is lacking. The main objective is to identify and analyze theoretical and practical components related to the detection and mitigation of biases and inequalities in machine learning. The proposed approach combines best practices, ethics, and technology to promote the responsible use of artificial intelligence in Colombia. The methodology covers the definition of performance and fairness interests, interventions in preprocessing, processing, and post-processing, and the generation of recommendations and explainability of the model.