In real-world recommendation systems, users engage in a variety of scenarios, such as homepages, search pages, and related-item recommendation pages. Each of these scenarios is designed to capture distinct facets of user intent. However, user interests are often inconsistent across different scenarios, attributable to variations in their decision-making processes and modes of preference expression. This inherent heterogeneity poses a substantial challenge to unified modeling, rendering multi-scenario recommendation a non-trivial task. To address these challenges, we propose RUIE, a novel reinforcement learning-enhanced framework that models dynamic user preference evolution as sequential decision-making problems, and leverages cross-scenario behavior sequences to detect interest shifts and dynamically adjust sample utilization for accurate interest capture. Experiments demonstrate that our proposed approach significantly outperforms state-of-the-art methods in multi-scenario recommendation tasks and is widely applicable. This work offers a fresh perspective on multi-scenario modeling and highlights promising directions for future research. The source code is available at https://github.com/rl4rec/RUIE.

Recommender systems are essential for modern content platforms, yet traditional behavior-based models often struggle with cold users who have limited interaction data. Engaging these users is crucial for platform growth. To bridge this gap, we propose leveraging the social-relation graph to enrich interest representations from behavior-based models. However, extracting value from social graphs is challenging due to relation noise and cross-domain inconsistency. To address the noise propagation and obtain accurate social interest, we employ a dual-view denoising strategy, employing low-rank SVD to the user-item interaction matrix for a denoised social graph and contrastive learning to align the original and reconstructed social graphs. Addressing the interest inconsistency between social and behavioral interests, we adopt a ''mutual distillation'' technique to isolate the original interests into aligned social/behavior interests and social/behavior specific interests, maximizing the utility of both. Experimental results on widely adopted industry datasets verify the method's effectiveness, particularly for cold users, offering a fresh perspective for future research. The implementation can be accessed at https://github.com/WANGLin0126/CLSRec.

Recommendation systems play a vital role in many online platforms, with their primary objective being to satisfy and retain users. As directly optimizing user retention is challenging, multiple evaluation metrics are often employed. Current methods often use multi-task learning to optimize these measures. However, they usually miss that users have personal preferences for different tasks, which can change over time. Identifying and tracking the evolution of user preferences can lead to better user retention. To address this issue, we introduce the concept of “user lifecycle,” consisting of multiple stages characterized by users’ varying preferences for different tasks. We propose a novel Stage-Adaptive Network (STAN) framework for modeling user lifecycle stages. STAN first identifies latent user lifecycle stages based on learned user preferences and then employs the stage representation to enhance multi-task learning performance. Our experimental results using both public and industrial datasets demonstrate that the proposed model significantly improves multi-task prediction performance compared to state-of-the-art methods, highlighting the importance of considering user lifecycle stages in recommendation systems. Online A/B testing reveals that our model outperforms the existing model, achieving a significant improvement of 3.05% in staytime per user and 0.88% in CVR. We have deployed STAN on all Shopee live-streaming recommendation services.

Recommendation with multiple objectives is an important but difficult problem, where the coherent difficulty lies in the possible conflicts between objectives. In this case, multi-objective optimization is expected to be Pareto efficient, where no single objective can be further improved without hurting the others. However existing approaches to Pareto efficient multi-objective recommendation still lack good theoretical guarantees.