Today’s machine learning models possess remarkable predictive performance, but are often unable to explain the “how” and “why” behind their predictions. In this talk Professor Müller will give an introduction to the topic of interpretable machine learning. The talk will cover the concept of interpretability, approaches and methods for interpreting black-box machine learning models, and a discussion of when and why we need interpretability.
About:
Oliver Müller is a Professor of Management Information Systems and Data Analytics at Paderborn University. In his research he studies how organizations create value with (big) data and analytics; for example, by enhancing judgment and decision making, supporting knowledge management, or automating business processes. His research has been published in the Journal of Management Information Systems, Journal of the Association of Information Systems, European Journal of Information Systems, and various others.