Individual and Group Decision Making and Recommender Systems

Given that an important function of recommender systems is to help people make better choices, people who design and study recommender systems ought to have a good understanding of how people make choices and how human choice can be supported. This chapter uses an accessible summary of what is known about these topics as a framework for discussing the implications of this knowledge for the design of recommender systems. The first half of the chapter focuses on choices made by individuals, providing a compact update of the corresponding chapter in the previous edition of this handbook. The second half of the chapter extends the analysis to choices made by groups and their support by recommender systems for groups. Each half is organized in terms of two previously published models that make the relevant knowledge from psychology and related fields accessible to those who work on recommender systems and other interactive computing technology. The Aspect model distinguishes six choice patterns that together capture the wide variety of ways in which people make choices; the model enables us to identify both familiar and novel ways in which recommender systems can support choice. The Arcades model distinguishes seven high-level choice support strategies; whereas one of the strategies is already widely used in recommender systems, the other strategies can help round out the choice support that a recommender system offers.