Building User Trust in Recommendations via Fairness and Explanations

This course aims to teach techniques for increasing user trust in recommender systems by focusing on fairness aspects and explanation approaches. The learning outcomes include understanding fairness in AI systems, ethical principles, fairness of utility and exposure, taxonomy of fairness in recommendations, and explaining recommendations using white box vs black-box models, local proxy models, and counterfactual explanations. The teaching method involves discussing these concepts and techniques in a workshop format. The intended audience includes individuals interested in AI ethics, fairness in AI systems, and improving user trust in recommender systems.