Lv Shao

Chen Gao, Zixin Zhao, Lv Shao et al.

In e-commerce, Trigger-Induced Recommendation (TIR), recommending items after a user clicks a trigger, is an important task. However, modern platforms rely on a continuous stream of diverse and short-lived promotional scenarios (e.g., for Black Friday), creating a significant challenge. Existing methods are less effective here: they either fall into a trigger-dependency trap, recommending overly similar items, or a data-hungry trap, requiring long-term stable data for intent modeling that these ephemeral scenarios cannot provide. To address these limitations, we propose the Collaborative Contrastive Network (CCN), a general and robust framework that approaches the problem from a different perspective. Instead of modeling ambiguous entry intent, CCN learns a user's context-specific preferences by treating the user-trigger pair as a unique condition. It achieves this via a novel contrastive learning scheme, using the collaborative feedback of co-click/co-non-click as a positive signal and mono-click as a negative signal to structure the item representation latent space. To prove its real-world generality, CCN is trained on a heterogeneous dataset spanning over a dozen different scenarios from an entire year, and the online A/B test is conducted in a completely new, unseen scenario on Taobao, where CCN boosts CTR by 12.3\% and order volume by 12.7\%, demonstrating its effectiveness and generalization.

Chen Gao, Zixin Zhao, Lv Shao et al.

Click-Through Rate (CTR) prediction has long been dominated by discriminative paradigms that optimize local decision boundaries within candidate-specific subspaces. However, these models often fail to capture the global joint distribution and the continuous structural evolution of user intent across all-domain movelines. While generative approaches attempt to model global transition patterns, existing methods suffer from discretization-induced information collapse by remapping nuanced e-commerce signals into discrete linguistic or categorical spaces, failing to preserve the topological fidelity of interest trajectories. To overcome these limitations, we propose a novel generative pre-training paradigm that models user intent as a continuous evolutionary trajectory on a high-dimensional latent interest manifold, termed the Next Interest Flow (NIF). We introduce kinematic constraints to govern this flow: Interest Diversity is achieved via tangent space decomposition, while Evolution Velocity ensures trajectory smoothness through geodesic regularization. To bridge the objective mismatch between generative pre-training and discriminative fine-tuning, we propose a bidirectional alignment strategy to synchronize semantic spaces. Furthermore, we develop a Temporal Sequential Pairwise (TSP) mechanism to instill temporal causality within the discriminative framework. We present the All-domain Moveline Evolution Network (AMEN), a unified framework implementing this pipeline. Extensive experiments on a 6.7-billion instance industrial dataset and online A/B tests on Taobao validate AMEN's superiority, achieving +0.87pt AUC gain and +11.6\% CTCVR lift.

Chen Gao, Zixin Zhao, Lv Shao et al.

E-commerce app users exhibit behaviors that are inherently logically consistent. A series of multi-scenario user behaviors interconnect to form the scene-level all-domain user moveline, which ultimately reveals the user's true intention. Traditional CTR prediction methods typically focus on the item-level interaction between the target item and the historically interacted items. However, the scene-level interaction between the target item and the user moveline remains underexplored. There are two challenges when modeling the interaction with preceding all-domain user moveline: (i) Heterogeneity between items and scenes: Unlike traditional user behavior sequences that utilize items as carriers, the user moveline utilizes scenes as carriers. The heterogeneity between items and scenes complicates the process of aligning interactions within a unified representation space. (ii) Temporal misalignment of linked scene-level and item-level behaviors: In the preceding user moveline with a fixed sampling length, certain critical scene-level behaviors are closely linked to subsequent item-level behaviors. However, it is impossible to establish a complete temporal alignment that clearly identifies which specific scene-level behaviors correspond to which item-level behaviors. To address these challenges and pioneer modeling user intent from the perspective of the all-domain moveline, we propose All-domain Moveline Evolution Network (AMEN). AMEN not only transfers interactions between items and scenes to homogeneous representation spaces, but also introduces a Temporal Sequential Pairwise (TSP) mechanism to understand the nuanced associations between scene-level and item-level behaviors, ensuring that the all-domain user moveline differentially influences CTR predictions for user's favored and unfavored items. Online A/B testing demonstrates that our method achieves a +11.6% increase in CTCVR.

Yutong Li, Yu Zhu, Yichen Qiao et al.

The pre-ranking stage in industrial recommendation systems faces a fundamental conflict between efficiency and effectiveness. While powerful models like Target Attention (TA) excel at capturing complex feature interactions in the ranking stage, their high computational cost makes them infeasible for pre-ranking, which often relies on simplistic vector-product models. This disparity creates a significant performance bottleneck for the entire system. To bridge this gap, we propose TARQ, a novel pre-ranking framework. Inspired by generative models, TARQ's key innovation is to equip pre-ranking with an architecture approximate to TA by Residual Quantization. This allows us to bring the modeling power of TA into the latency-critical pre-ranking stage for the first time, establishing a new state-of-the-art trade-off between accuracy and efficiency. Extensive offline experiments and large-scale online A/B tests at Taobao demonstrate TARQ's significant improvements in ranking performance. Consequently, our model has been fully deployed in production, serving tens of millions of daily active users and yielding substantial business improvements.