Transparency in Fair Machine Learning: the Case of Explainable Recommender Systems

Abstract

Machine Learning (ML) models are increasingly being used in many sectors, ranging from health and education to justice and criminal investigation. Therefore, building a fair and transparent model which conveys the reasoning behind its predictions is of great importance. This chapter discusses the role of explanation mechanisms in building fair machine learning models and explainable ML technique. We focus on the special case of recommender systems because they are a prominent example of a ML model that interacts directly with humans. This is in contrast to many other traditional decision making systems that interact with experts (e.g. in the health-care domain). In addition, we discuss the main sources of bias that can lead to biased and unfair models. We then review the taxonomy of explanation styles for recommender systems and review models that can provide explanations for their recommendations. We conclude by reviewing evaluation metrics for assessing the power ofExplainability explainability in recommender systems.