Ephemeral State-Dependent Recommendation for Digital Content

Building upon recent advances in consumption theories, we propose an ephemeral state-dependent framework for digital content recommendations. The framework accentuates a critical, yet understudied, interplay between a firm’s recommendation strategy (assimilation or diversification) and a consumer’s ephemeral state. This temporary state is gauged by the breadth of a consumer’s ephemeral preference at the moment of choice—either fixation on a single type of content or foraging across types. The framework adaptively recommends either assimilated or diversified content based on a consumer’s ephemeral state, accomplishing effective strategy-state pairing. A large-scale randomized field experiment in collaboration with a leading e-book platform demonstrates the consumption and profit impacts of such state-dependent recommendations. Although the strategy-state congruent scheme (i.e., assimilation when fixation, diversification when foraging) is overall superior, the incongruent scheme (i.e., assimilation when foraging, diversification when fixation) is more desirable for consumers with a more fluid or broader preference, revealing consumer heterogeneity and needs for refined personalization. We further demonstrate nuanced spillover effects on the nonrecommended content. This research contributes to the literature by incorporating theory-driven designs into recommender systems and providing important managerial insights for the digital content industry.

History: Olivia Liu Sheng, Senior Editor; Jingjing Zhang, Associate Editor.

Funding: Y. Li received financial support from the National Natural Science Foundation of China [Grants 72071192, 72188101, and 72091210].

Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2022.664.