Modeling Churn in Recommender Systems with Aggregated Preferences
This addresses churn risk in recommender systems for users and platforms under data aggregation constraints, but it is incremental as it builds on existing exploration-exploitation frameworks.
The paper tackles the problem of user churn in recommender systems when relying on aggregated user data by proposing a model that balances exploration and exploitation. It demonstrates that optimal policies transition from exploration to exploitation in finite time and validates the approach empirically.
While recommender systems (RSs) traditionally rely on extensive individual user data, regulatory and technological shifts necessitate reliance on aggregated user information. This shift significantly impacts the recommendation process, requiring RSs to engage in intensive exploration to identify user preferences. However, this approach risks user churn due to potentially unsatisfactory recommendations. In this paper, we propose a model that addresses the dual challenges of leveraging aggregated user information and mitigating churn risk. Our model assumes that the RS operates with a probabilistic prior over user types and aggregated satisfaction levels for various content types. We demonstrate that optimal policies naturally transition from exploration to exploitation in finite time, develop a branch-and-bound algorithm for computing these policies, and empirically validate its effectiveness.