FairDETOCS: An approach to detect and connect unfair models

In the dawn of the digital age, Artificial Intelli-gence and decision-making systems have become omnipresent, completely shaping various aspects of our daily lives. Unfortu-nately, as these systems grow more complex and influential, they also raise significant ethical and societal concerns. As machine learning and AI continue to evolve, ensuring fairness in these systems has become increasingly important. The challenge lies in making models fair, necessitating algorithms that mitigate biases, particularly intersectional biases. Numerous studies have highlighted the lack of intersectional bias treatment in current methodologies. Thus, we propose in this paper a novel approach named FairDetocs. This method incorporates fairness metrics to measure intersectional biases and employs a reweighting algorithm to mitigate them. The process begins with the initial evaluation of biases, followed by data adjustment through the reweighting algorithm, and concludes with a re-evaluation of biases to ensure effective reduction. We base our study on the Adult Income dataset, modified with Canadian statistics. Our results demonstrate a noticeable attenuation of biases, showcasing the effectiveness of FairDetocs in promoting fairness in machine learning models. Overall, our exploratory study provides a significant contribution to the field of fairness in machine learning and sets the stage for further research on this topic.