Metraipolis › archive › dc_c21e35784337
RedMall: Generative Recommendation for Large-Scale E-commerce — arXiv:2611.08519
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.08519
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:44:53.641Z
- SHA-256 of the archived text
f653505def9414b40b3a255af16eef32d26f73348a7b4ebbdffecd64908158e2- Stable URL of this page
https://metraipolis.com/documento/dc_c21e35784337
How to cite
RedMall: Generative Recommendation for Large-Scale E-commerce — arXiv:2611.08519 — arXiv (en), https://arxiv.org/abs/2611.08519 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c21e35784337 (Metraipolis archive dc_c21e35784337, sha256 f653505def9414b40b3a255af16eef32d26f73348a7b4ebbdffecd64908158e2)
BibTeX
@misc{dcc21e35784337,
title = {RedMall: Generative Recommendation for Large-Scale E-commerce — arXiv:2611.08519},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.08519},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c21e35784337; sha256 f653505def9414b40b3a255af16eef32d26f73348a7b4ebbdffecd64908158e2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08519. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative recommendation has shown considerable potential in industrial recommendation systems. However, the performance of existing generative methods is limited by several challenges. 1) Semantic IDs (SIDs) are treated as one-dimensional sequences, overlooking the hierarchical dependencies among different layers. 2) Next-token prediction used is unable to explicitly optimize session-wise recommendation. 3) Although reinforcement learning has been applied to align generated recommendations with user preferences, few existing methods explicitly optimize the ranking of positive items in session-wise recommendation. To address the above issues, we propose RedMall, a generative recommender designed for large-scale e-commerce. Firstly, RedMall constructs hierarchical SIDs through residual quantization over multimodal representations. Secondly, RedMall introduces a lightweight SID encoder to explicitly model layer-wise dependencies in SIDs. Moreover, RedMall incorporates sparse mixture-of-experts, dual gated attention, and multi-target prediction to scale model size, enhance user interest representation, and optimize session-wise recommendation. We further design an exposure-aware loss that treats exposed but unclicked items as negative feedback. To better align user preferences and list-wise ranking objectives, we combine Group Relative Policy Optimization with an auxiliary LambdaRank loss, using both real user feedback and item ranking to guide optimization. Experiments on four public datasets-Amazon Beauty, Amazon Toys, Amazon Food, and MovieLens-1M---show that RedMall outperforms the evaluated baselines across all reported Recall and NDCG metrics. Online A/B tests show improvements of 2.24% in advertiser value (ADVV) and 0.59% in click-through rate (CTR) for e-commerce advertising, as well as gains of 1.08% in GMV and 0.95% in daily active buyers (DAB) for e-commerce recommendations. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2611.08519 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:37:32.230Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).