Transparent Personalization in E-Commerce
In the project "TransPer: Transparent Personalization in E-Commerce" aspects of causality, robustness and uncertainty of AI applications in an industrial environment are considered. The project specifically focuses on how product recommendations in the e-commerce sector can be made more transparent in order to achieve better customer satisfaction and to ensure compliance with legal requirements. In the project, the KIT Institute AIFB under the direction of Dr. Färber develops modules to make product recommendations in online web shops transparent. Econda GmbH, which works with around 20% of all German online shops, acts as an industrial partner.
inproceedingsAnna Nguyen, Franz Krause, Daniel Hagenmayer, Michael Färber
Quantifying Explanations of Neural Networks in E-Commerce Based on LRP
Proceedings of Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD'21), Springer, Juli, 2021