The Decoy Effect and Recommendation Systems

Abstract

In this paper, we explore the decoy effect in recommendation systems. Including a decoy item in a set of alternatives can influence the attractiveness of the other items by facilitating decision making. Prior research literature has indeed shown the decoy effect to be robust in traditional choice settings, with consistent reporting of an overall positive impact. Practitioners often use decoys to help drive demand for specific items. Recommendation systems too are increasingly being used to present item choice sets to customers and users. Both recommendation systems and the decoy effect can be used as strategies to help facilitate decision making. However, previous work has not examined the decoy effect in the context of recommendations. The decoy effect may facilitate consumer decision making and positively impact user behavior when used with recommendation systems. However, in the recommendation context, customers often have different expectations for the reliability and quality of the presented information. Hence, a decoy as a recommendation could signal issues in system reliability, resulting in a negative effect. We perform a randomized, controlled laboratory experiment and use persuasion theory as the theoretical lens to demonstrate that the decoy effect works differently in the context of recommendation systems. Specifically, we show that depending on the recommendation context, the decoy effect can or cannot drive demand for target items. We find that including a decoy minimizes the demand for the target option when personalized recommendations are presented, which deviates from the traditional decoy effect. However, a decoy increases the target’s demand when nonpersonalized recommendations are shown, following the conventional decoy effect. We explore the mechanism behind these findings and show the robustness of our results by conducting multiple analyses and additional experiments. The findings of our paper have important implications for the design of recommendation systems and our understanding of consumer decision making. History: Ravi Bapna, Senior Editor; Idris Adjerid, Associate Editor. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2022.1197.