Context-based Fast Recommendation Strategy for Long User Behavior Sequence in Meituan Waimai
Abstract: In the recommender system of Meituan Waimai, we are dealing with ever-lengthening user behavior sequences, which pose an increasing challenge to modeling user preference effectively. Existing sequential recommendation models often fail to capture long-term dependencies or are too complex, complicating the fulfillment of Meituan Waimai's unique business needs. To better model user interests, we consider selecting relevant sub-sequences from users' extensive historical behaviors based on their preferences. In this specific scenario, we've noticed that the contexts in which users interact have a significant impact on their preferences. For this purpose, we introduce a novel method called Context-based Fast Recommendation Strategy to tackle the issue of long sequences. We first identify contexts that share similar user preferences with the target context and then locate the corresponding PoIs based on these identified contexts. This approach eliminates the necessity to select a sub-sequence for every candidate PoI, thereby avoiding high time complexity. Specifically, we implement a prototype-based approach to pinpoint contexts that mirror similar user preferences. To amplify accuracy and interpretability, we employ JS divergence of PoI attributes such as categories and prices as a measure of similarity between contexts. A temporal graph integrating both prototype and context nodes helps incorporate temporal information. We then identify appropriate prototypes considering both target contexts and short-term user preferences. Following this, we utilize contexts aligned with these prototypes to generate a sub-sequence, aimed at predicting CTR and CTCVR scores with target attention. Since its inception in 2023, this strategy has been adopted in Meituan Waimai's display recommender system, leading to a 4.6% surge in CTR and a 4.2% boost in GMV.
- Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction. In CIKM. ACM, 2974–2983.
- Sequential Recommendation with Graph Neural Networks. In SIGIR. ACM, 378–387.
- TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou. In KDD. ACM, 3785–3794.
- End-to-End User Behavior Retrieval in Click-Through RatePrediction Model. abs/2108.04468 (2021).
- Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions. In AAAI. AAAI Press, 3609–3616.
- Deep Neural Networks for YouTube Recommendations. In RecSys. ACM, 191–198.
- Session-based Recommendations with Recurrent Neural Networks. In ICLR.
- J. Wesley Hines. 1996. A logarithmic neural network architecture for unbounded non-linear function approximation. In ICNN. IEEE, 1245–1250.
- Interaction-Aware Factorization Machines for Recommender Systems. In AAAI. AAAI Press, 3804–3811.
- Categorical Reparameterization with Gumbel-Softmax. In ICLR (Poster). OpenReview.net.
- Field-aware Factorization Machines for CTR Prediction. In RecSys. ACM, 43–50.
- Wang-Cheng Kang and Julian J. McAuley. 2018. Self-Attentive Sequential Recommendation. In ICDM. 197–206.
- Neural Attentive Session-based Recommendation. In CIKM. ACM, 1419–1428.
- Prototypical Contrastive Learning of Unsupervised Representations. In ICLR. OpenReview.net.
- Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction. In SIGIR. ACM, 1969–1973.
- Lightweight Self-Attentive Sequential Recommendation. In CIKM. ACM, 967–977.
- xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems. In KDD. ACM, 1754–1763.
- Non-invasive Self-attention for Side Information Fusion in Sequential Recommendation. CoRR abs/2103.03578 (2021).
- A Dual Input-aware Factorization Machine for CTR Prediction. In IJCAI. ijcai.org, 3139–3145.
- Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction. In KDD. ACM, 2671–2679.
- Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction. In CIKM. ACM, 2685–2692.
- The World is Binary: Contrastive Learning for Denoising Next Basket Recommendation. In SIGIR. 859–868.
- Context and Attribute-Aware Sequential Recommendation via Cross-Attention. In RecSys. ACM, 71–80.
- Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction. In SIGIR. ACM, 565–574.
- Sequential Recommendation with Self-Attentive Multi-Adversarial Network. In SIGIR. ACM, 89–98.
- Steffen Rendle. 2010. Factorization Machines. In ICDM. IEEE Computer Society, 995–1000.
- Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce. In WSDM. ACM, 937–946.
- BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer. In CIKM. 1441–1450.
- EulerNet: Adaptive Feature Interaction Learning via Euler’s Formula for CTR Prediction. In SIGIR. ACM, 1376–1385.
- Pattern-enhanced Contrastive Policy Learning Network for Sequential Recommendation. In IJCAI. ijcai.org, 1593–1599.
- Graph Attention Networks. In ICLR. OpenReview.net.
- Characterizing context-aware recommender systems: A systematic literature review. Knowl. Based Syst. 140 (2018), 173–200.
- DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems. In WWW. ACM / IW3C2, 1785–1797.
- Session-Based Recommendation with Graph Neural Networks. In AAAI. AAAI Press, 346–353.
- Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention. CoRR abs/2105.14060 (2021).
- Feature-level Deeper Self-Attention Network for Sequential Recommendation. In IJCAI. ijcai.org, 4320–4326.
- Clustering based Behavior Sampling with Long Sequential Data for CTR Prediction. In SIGIR. ACM, 2195–2200.
- Deep Interest Evolution Network for Click-Through Rate Prediction. In AAAI. AAAI Press, 5941–5948.
- Deep Interest Network for Click-Through Rate Prediction. In KDD. ACM, 1059–1068.
- A Comprehensive Survey on Transfer Learning. Proc. IEEE 109, 1 (2021), 43–76.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.