Shared-account usage is common on short-video platforms, especially on mobile and tablet devices, where a single device is accessed by multiple users. While existing industrial solutions generally focus on behavior sequence purification to disentangle mixed user preferences, such approaches inherently depend on behavior accumulation and therefore lack the capability for real-time user identification. To adapt to online recommendation, utilizing gesture interaction features is a natural and promising option, as they (1) are instantaneous without behavior collection and (2) naturally encode fine-grained user operation habits. Nevertheless, we empirically observe that directly incorporating raw gesture features into recommendation models yields limited gains. Identity-discriminative patterns embedded in gesture signals are largely entangled during the main model training, preventing them from being leveraged as explicit and reliable identity cues. As a result, efficiently utilizing gesture information to provide more distinct identity signals for recommendation models remains a critical challenge. To address this issue, we propose G-CORE (Gesture Clustering for Real-time REcommendation), an unsupervised framework that disentangles gesture representations via clustering before integrating them into the main recommendation model. By providing clearer and more identity-aware signals, G-CORE enables the main model with faster user switching without relying on a volume of behavior accumulation. Through extensive offline experiments and online A/B tests on Kuaishou platform, G-CORE demonstrates its effectiveness in various shared-account scenarios, and has been successfully deployed in the Mobile and Tablet system of the platform.

With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumption platforms (e.g., short video platforms). However, short videos often contain diverse segments, and users may not hold the same attitude toward all of them (e.g., music enthusiasts may not enjoy all songs in a medley). Traditional binary-classification recommendation models, which treat a video as a single holistic entity, face limitations in accurately capturing such nuanced preferences. Considering that user consumption is a temporal process, this paper demonstrates that the timing of user actions can represent diverse intentions through statistical analysis and examination of action patterns. Based on this insight, we propose a novel modeling paradigm: Action-Aware Gen erative Sequence Network (A2Gen ), which refines user actions (e.g., Like and Follow, etc.) along the temporal dimension and chains them into sequences for unified processing and prediction. First, we introduce the Context-aware Attention Module (CAM) to model action sequences enriched with item-specific contextual features. Building upon this, we develop the Hierarchical Sequence Encoder (HSE) to learn temporal action patterns from users' historical actions. Finally, through leveraging CAM, we design a module for action sequence generation: the Action-seq Autoregressive Generator (AAG). Extensive offline experiments on the Kuaishou's dataset and the Tmall public dataset demonstrate the superiority of our proposed model. Furthermore, through large-scale online A/B testing deployed on Kuaishou's platform, our model achieves significant improvements over baseline methods in multi-task prediction by leveraging sequential information. Specifically, it yields increases of 0.34% in user watch time, 8.1% in interaction rate, and 0.162% in overall user retention (LifeTime-7), leading to successful deployment across all traffic, serving over 400 million users every day.

Short-video recommender systems typically optimize ranking models using dense user behavioral signals, such as clicks and watch time. However, these signals are only indirect proxies of user satisfaction and often suffer from noise and bias. Recently, explicit satisfaction feedback collected through questionnaires has emerged as a high-quality direct alignment supervision, but is extremely sparse and easily overwhelmed by abundant behavioral data, making it difficult to incorporate into online recommendation models. To address these challenges, we propose a novel framework which is towards End-to-End Alignment of user Satisfaction via Questionnaire, named EASQ, to enable real-time alignment of ranking models with true user satisfaction. Specifically, we first construct an independent parameter pathway for sparse questionnaire signals by combining a multi-task architecture and a lightweight LoRA module. The multi-task design separates sparse satisfaction supervision from dense behavioral signals, preventing the former from being overwhelmed. The LoRA module pre-inject these preferences in a parameter-isolated manner, ensuring stability in the backbone while optimizing user satisfaction. Furthermore, we employ a DPO-based optimization objective tailored for online learning, which aligns the main model outputs with sparse satisfaction signals in real time. This design enables end-to-end online learning, allowing the model to continuously adapt to new questionnaire feedback while maintaining the stability and effectiveness of the backbone. Extensive offline experiments and large-scale online A/B tests demonstrate that EASQ consistently improves user satisfaction metrics across multiple scenarios. EASQ has been successfully deployed in a production short-video recommendation system, delivering significant and stable business gains.

User retention is critical in large-scale recommender systems, significantly influencing online platforms' long-term success. Existing methods typically focus on short-term engagement, neglecting the evolving dynamics of user behaviors over time. Reinforcement learning (RL) methods, though promising for optimizing long-term rewards, face challenges like delayed credit assignment and sample inefficiency. We introduce Stratified Expert Cloning (SEC), an imitation learning framework that leverages abundant interaction data from high-retention users to learn robust policies. SEC incorporates: 1) multi-level expert stratification to model diverse retention behaviors; 2) adaptive expert selection to dynamically match users with appropriate policies based on their state and retention history; and 3) action entropy regularization to enhance recommendation diversity and policy generalization. Extensive offline evaluations and online A/B tests on major video platforms (Kuaishou and Kuaishou Lite) with hundreds of millions of users validate SEC's effectiveness. Results show substantial improvements, achieving cumulative lifts of 0.098% and 0.122% in active days on the two platforms respectively, each translating into over 200,000 additional daily active users.

In scenarios involving sequence recommendations on large screen devices, such as tablets or TVs, the equipment is often shared among multiple users. This sharing leads to a mixture of behaviors from different users, posing significant challenges to recommendation systems, especially when clear supervisory signals for distinguishing among users are absent. Current solutions tend to either operate in an unsupervised manner or rely on constructed supervisory signals that are not entirely reliable. Moreover, the peculiarities of short video recommendations in this context have not been thoroughly explored in existing research. In response to these challenges, this paper introduces Multi-User Contrastive Decoupling Model (MODEM), a novel short video recommendation model specifically designed for large screen devices. MODEM leverages an attention mechanism, grounded in session segmentation, to disentangle the intertwined user behavior histories. It also discriminates between the impacts of long and short viewing behaviors on short video recommendations by cross-analyzing sequences of both. Furthermore, we have developed a contrastive learning method to oversee the decoupling of user behaviors effectively. Our evaluations demonstrate noticeable improvements through both offline assessments within public datasets and online A/B testing within Kuaishou’s short video recommendation environment on large screen devices. Specifically, our online A/B tests resulted in a 0.55% increase in watch time. These results underscore MODEM’s efficacy in enhancing recommendation quality in shared account contexts.