Nudging in recommender systems: how effective is nudging in decision environments that offer personalized recommendations?

TUM Main Campus
Room 2544 (Entrance Luisenstraße)
Arcisstraße 21
80333 München
23 Nov 2022
3:00 pm (Central European Time)

Authors: Martijn Willemsen (Eindhoven University of Technology)


Abstract: Behavioral economics and decision making research has been discussing how the choice environment shapes decisions for decades. Concepts such as preference construction, nudges and choice architectures have shaped our understanding of how decision makers discover what they want and how the environment influences their choices. However, many of these techniques and nudges (like defaults) are often ‘one size fits all’. With the increased use of AI technologies such as recommender systems, digital nudging has been proposed as a way to provide personalized choice architecture tools. However, this has made some scholars worried about ‘hyper-nudging’: people being manipulated via subtle but very effectively targeted nudges. In this talk I will discuss my work on recommender systems and (digital) nudging. As recommender systems personalize the type of recommendations provided to the user, the question arises how much nudging is still needed if the personalization is effective. I will discuss work on energy saving recommendations and music genre explorations, two domains in which recommender systems can be used to help users go beyond their current preferences/behavior. We found that in these domains nudges add value by helping people through more effective choices and exploration, but that in general adequate personalization is key for better decisions.


Host: Christoph Ungemach