# Churn-Aware Recommendation Planning under Aggregated Preference Feedback

arXiv: https://arxiv.org/abs/2507.04513 · HTML: https://mlsanity.com/paper/2507.04513/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 6 Jul 2025.

## Builds on (most cited first, 16 of 16)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Meta Matrix Factorization for Federated Rating Predictions](https://mlsanity.com/paper/1910.10086/) (2019)
- [Learning to branch with Tree MDPs](https://mlsanity.com/paper/2205.11107/) (2022)
- [Task-adaptive Neural Process for User Cold-Start Recommendation](https://mlsanity.com/paper/2103.06137/) (2021)
- [Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users](https://mlsanity.com/paper/2105.04785/) (2021)
- [Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories](https://mlsanity.com/paper/2205.14345/) (2022)
- [Personalized Adaptive Meta Learning for Cold-start User Preference Prediction](https://mlsanity.com/paper/2012.11842/) (2020)
- [A Heterogeneous Information Network based Cross Domain Insurance Recommendation System for Cold Start Users](https://mlsanity.com/paper/2007.15293/) (2020)
- [Optimal Recommendation to Users that React: Online Learning for a Class of POMDPs](https://mlsanity.com/paper/1603.09233/) (2016)
- [Partially Observable Markov Decision Process for Recommender Systems](https://mlsanity.com/paper/1608.07793/) (2016)
- [Modeling Attrition in Recommender Systems with Departing Bandits](https://mlsanity.com/paper/2203.13423/) (2022)
- [Fatigue-aware Bandits for Dependent Click Models](https://mlsanity.com/paper/2008.09733/) (2020)
- [Goodbye Tracking? Impact of iOS App Tracking Transparency and Privacy Labels](https://mlsanity.com/paper/2204.03556/) (2022)
- [Maximizing Cumulative User Engagement in Sequential Recommendation: An Online Optimization Perspective](https://mlsanity.com/paper/2006.04520/) (2020)
- [Interactive and Explainable Point-of-Interest Recommendation using Look-alike Groups](https://mlsanity.com/paper/2009.00099/) (2020)
- [Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalization](https://mlsanity.com/paper/2310.04015/) (2023)

## Abstract (arXiv)

We study a sequential decision-making problem motivated by recent regulatory and technological shifts that limit access to individual user data in recommender systems (RSs), leaving only population-level preference information. This privacy-aware setting poses fundamental challenges in planning under uncertainty: Effective personalization requires exploration to infer user preferences, yet unsatisfactory recommendations risk immediate user churn. To address this, we introduce the Rec-APC model, in which an anonymous user is drawn from a known prior over latent user types (e.g., personas or clusters), and the decision-maker sequentially selects items to recommend. Feedback is binary -- positive responses refine the posterior via Bayesian updates, while negative responses result in the termination of the session. We prove that optimal policies converge to pure exploitation in finite time and propose a branch-and-bound algorithm to efficiently compute them. Experiments on synthetic and MovieLens data confirm rapid convergence and demonstrate that our method outperforms the POMDP solver SARSOP, particularly when the number of user types is large or comparable to the number of content categories. Our results highlight the applicability of this approach and inspire new ways to improve decision-making under the constraints imposed by aggregated preference data.