While personalization increases the utility of recommender systems, it also brings the issue offilter bubbles. e.g., if the system keeps exposing and recommending the items that the user is interested in, it may also make the user feel bored and less satisfied. Existing work studies filter bubbles in static recommendation, where the effect of overexposure is hard to capture. In contrast, we believe it is more meaningful to study the issue in interactive recommendation and optimize long-term user satisfaction. Nevertheless, it is unrealistic to train the model online due to the high cost. As such, we have to leverage offline training data and disentangle the causal effect on user satisfaction. To achieve this goal, we propose a counterfactual interactive recommender system (CIRS) that augments offline reinforcement learning (offline RL) with causal inference. The basic idea is to first learn a causal user model on historical data to capture the overexposure effect of items on user satisfaction. It then uses the learned causal user model to help the planning of the RL policy. To conduct evaluation offline, we innovatively create an authentic RL environment (KuaiEnv) based on a real-world fully observed user rating dataset. The experiments show the effectiveness of CIRS in bursting filter bubbles and achieving long-term success in interactive recommendation. The implementation of CIRS is available via https://github.com/chongminggao/ CIRS-codes.

Offline reinforcement learning (RL), a technology that offline learns a policy from logged data without the need to interact with online environments, has become a favorable choice in decision-making processes like interactive recommendation. Offline RL faces the value overestimation problem. To address it, existing methods employ conservatism, e.g., by constraining the learned policy to be close to behavior policies or punishing the rarely visited state-action pairs. However, when applying such offline RL to recommendation, it will cause a severe Matthew effect, i.e., the rich get richer and the poor get poorer, by promoting popular items or categories while suppressing the less popular ones. It is a notorious issue that needs to be addressed in practical recommender systems. In this paper, we aim to alleviate the Matthew effect in offline RL-based recommendation. Through theoretical analyses, we find that the conservatism of existing methods fails in pursuing users' long-term satisfaction. It inspires us to add a penalty term to relax the pessimism on states with high entropy of the logging policy and indirectly penalizes actions leading to less diverse states. This leads to the main technical contribution of the work: Debiased model-based Offline RL (DORL) method. Experiments show that DORL not only captures user interests well but also alleviates the Matthew effect. The implementation is available via https://github.com/chongminggao/DORL-codes.

With the increasingly fierce market competition, the free trial has been widely applied as an effective incentive strategy to attract users and promote products. By providing opportunities to experience goods without charge, a free trial offers adopters more direct contact with the products and thus raises their willingness to buy. However, as the key point in the promotion process, how to select proper adopters is rarely explored. Empirically winnowing users by their static demographic attributes is feasible but less effective due to the lack of consideration of personalized demands. In this work, we propose SMILE – a tailored free trial user selection model for finding the best adopters promptly. Based on the reinforcement learning (RL) technique, SMILE can consider long-run profits and rely on user-item interactions to suggest actions. Besides, since selecting adopters from the large user candidates set is time-consuming, we design a balanced tree structure that reformulates the user action space. The experimental analysis on three datasets demonstrates the proposed model's superiority and elucidates why reinforcement learning and tree structure can improve performance. Our study shows technical feasibility of constructing a more robust and intelligent user selection model and guides for investigating more marketing promotion strategies.