Merve Alanyali, PhD
Head of Data Science Research and Academic Partnerships at Allianz Personal
Merve Alanyali is Head of Data Science Academic Partnerships and Research at Allianz Personal with more than ten years of commercial and academic experience. She draws on an interdisciplinary background in computer science, complex systems and behavioural science. Prior to joining Allianz Personal, she completed her doctoral degree on “Quantifying human behaviour using online images” at the University of Warwick with Chancellor’s International Scholarship and The Alan Turing Institute Enrichment Scheme funding. Her work has been featured by television and press worldwide including coverage in Financial Times and Bloomberg Business.
All Sessions by Merve Alanyali, PhD
Beyond Interpretability: An Interdisciplinary Approach to Communicate Machine Learning Outcomes
<span class="etn-schedule-location"> <span class="firstfocus">Responsible AI</span> <span class="secfocus">All Levels</span> </span>Explainable AI (XAI) is one of the hottest topics 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, in addition to the brief summary of methods used to interpret machine learning model outcomes, I will cover how we extended the concept of XAI with our multidisciplinary collaboration. I will end my talk with reflections on the insights gained from setting up an interdisciplinary collaboration between industry and academia.
Beyond Interpretability: An Interdisciplinary Approach to Communicate Machine Learning Outcomes
<span class="etn-schedule-location"> <span class="firstfocus">Responsible AI</span> <span class="secfocus">All Levels</span> </span>Explainable AI (XAI) is one of the hottest topics 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, in addition to the brief summary of methods used to interpret machine learning model outcomes, I will cover how we extended the concept of XAI with our multidisciplinary collaboration. I will end my talk with reflections on the insights gained from setting up an interdisciplinary collaboration between industry and academia.