Business Driven Explainable AI

1.5 units

This course is designed to provide students with the essential skills and practical knowledge needed to apply Explainable AI (XAI) technologies to solve complex business challenges. It emphasizes the use of feature attribution methods such as SHAP, LIME, and Partial Dependence Plots (PDPs), as well as Counterfactual Analysis to interpret and demystify black-box models commonly used in business settings, such as finance, marketing, HR, and operations. Students will focus on real-world applications to make AI models transparent and interpretable, foster trust, and integrate human feedback through a human-in-the-loop approach. This course also explores the explainability-accuracy tradeoff, and robustness analysis to ensure responsible AI adoption. By the end of the course, students will be equipped to utilize XAI techniques to optimize business strategies, enhance model performance, and support ethical and data-driven decision-making across diverse business functions, ensuring AI-driven insights are both interpretable and actionable