Explaining explainability: an interdisciplinary approach to communicate machine learning outcomes

A talk by Merve Alanyali from Allianz Personal.

This session covers Explaining explainability: an interdisciplinary approach to communicate machine learning outcomes.

Explainable AI (XAI) is one of the hottest topics of interest among AI researchers and practitioners. These explanations however often focus solely around providing technical interpretations on how a given machine learning model generates a certain outcome. To take a step beyond these technical explanations, we, Allianz Personal data science team together with our collaborators from the University of Bristol, investigated explaining AI decision making through a socio-technical lens. In my talk, I will reflect on the insights gained from setting up an interdisciplinary collaboration between industry and academia as well as how we extended the concept of XAI with our multidisciplinary collaboration.

Technical Level: Introductory level/students (some technical knowledge needed)