Unlocking Scaling Law in Industrial Recommendation Systems with a Three-step Paradigm based Large User Model
Authors:
- Bencheng YanBYBencheng Yan
- Shilei LiuSLShilei Liu
- Zhiyuan ZengZZZhiyuan Zeng
- Zihao WangZWZihao Wang
- Yizhen ZhangYZYizhen Zhang
- Yujin YuanYYYujin Yuan
- Langming LiuLLLangming Liu
- Jiaqi LiuJLJiaqi Liu
- Di WangDWDi Wang
- Wenbo SuWSWenbo Su
- Wang PengjieWPWang Pengjie
- Jian XuJXJian Xu
Preprint
Abstract
Recent advancements in autoregressive Large Language Models (LLMs) have achieved significant milestones, largely attributed to their scalability, often referred to as the "scaling law". Inspired by these achievements, there has been a growing interest in adapting LLMs for Recommendation Systems (RecSys) by reformulating RecSys tasks into generative problems. However, these End-to-End Generative Recommendation (E2E-GR) methods tend to prioritize idealized goals, often at the expense of the practical advantages offered by traditional Deep Learning based Recommendation Models (DLRMs) in terms of in features, architecture, and practices. This disparity between idealized goals and practical needs introduces several challenges and limitations, locking the scaling law in industrial RecSys. In this paper, we introduce a large user model (LUM) that addresses these limitations through a three-step paradigm, designed to meet the stringent requirements of industrial settings while unlocking the potential for scalable recommendations. Our extensive experimental evaluations demonstrate that LUM outperforms both state-of-the-art DLRMs and E2E-GR approaches. Notably, LUM exhibits excellent scalability, with performance improvements observed as the model scales up to 7 billion parameters. Additionally, we have successfully deployed LUM in an industrial application, where it achieved significant gains in an A/B test, further validating its effectiveness and practicality.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Inductive Generative Recommendation via Retrieval-based SpeculationProceedings of the AAAI Conference on Artificial Intelligence, 2026
- Analysing The Impact of Sequence Composition on Language Model Pre-Training2024
- Scale Calibration of Deep Ranking Models2022
- DeepFM: A Factorization-Machine based Neural Network for CTR Prediction2017