Interpretable Machine Learning: Shapley Values (Seminar Slides)

Abstract

Machine learning (ML) algorithms utilize the power of computers to solve tasks that are beyond the grasp of classical statistical methods. However, ML is often perceived as a black-box, hindering its adoption.

This seminar demonstrates the use of Shapley values to interpret the outputs of ML models. With the help of interpretability methods, ML is becoming the primary tool of scientific discovery, through induction as well as abduction.

Keywords: Machine learning, interpretability, deduction, induction, abduction, attribution

JEL Classification: G0, G1, G2, G15, G24, E44