Transparency in Algorithmic Decision Making
ERCIM News No. 116 has just been published at https://ercim-news.ercim.eu/
This issue includes a Special Theme "Transparency in Algorithmic Decision Making", coordinated by the guest editors Andreas Rauber (TU Wien and SBA), Roberto Trasarti and Fosca Giannotti (ISTI-CNR), providing an overview of the range of activities in this domain.
The past decade has seen increasing deployment of powerful automated decision-making systems in settings ranging from smile detection on mobile phone cameras to control of safety-critical systems. While evidently powerful in solving complex tasks, these systems are typically completely opaque, i.e. they provide hardly any mechanisms to explore and understand their behaviour and the reasons underlying their decisions. This opaqueness raises numerous legal, ethical and practical concerns, which have led to initiatives and recommendations on how to address these problems, calling for greater scrutiny in the deployment of automated decision-making systems. Clearly, joint efforts are required across technical, legal, sociological and ethical domains to address these increasingly pressing issues.
Machines are becoming increasingly responsible for decisions within society. Various groups, including professional societies in the area of information technologies, data analytics researchers, industry, and the general public are realising the power and potential of these technologies, accompanied by a sense of unease and an awareness of their potential dangers. Algorithms acting as black boxes make decisions that we are keen to follow as they frequently prove to be correct. Yet, no system is fool proof. Errors do and will occur no matter how much the underlying systems mature and improve due ever more data being available to them and ever more powerful algorithms learning from them.