L3S Research Center -  RSS Feeds

Sie sind hier


L3S proposal will be funded by the Amazon Research Awards (ARA) program

L3S will be awarded with $80,000 USD in funding and additional $20,000 USD in AWS Promotional Credits to pursue the proposed research plan. L3S researchers will use the funding to develop algorithms for post-hoc explanations of black box rankers that are used in many application areas from search engines to recommender systems.

Today's algorithmic decision-making is prevalent in several fields, including medicine, automobiles and retail. On one hand, this is testament to the ever improving performance and capabilities of complex machine-learning models. On the other hand, the increased complexity has resulted in a lack of transparency and interpretability which has led to critical decision-making models being deployed as functional black boxes. Being able to explain the actions of such systems will help attribute liability, build trust, expose biases and in turn lead to improved models.