通过分析商品折扣率提升电商推荐转化率预测精度。
Cheaper is Better: A Discount-Aware Network for Conversion Rate Prediction in E-commerce Recommendation System
- 引入频域变换与去偏模块，捕捉折扣长期趋势并缓解数据偏差。
- 离线AUC提升1.61%，线上点击转化率增3.63%，成交额增2.23%。
- 适合关注促销策略与推荐系统融合的算法工程师参考。
后点击转化率（CVR）是在线推荐系统中的关键指标，面临数据稀疏、样本选择偏差和延迟反馈等挑战。然而，影响价格与用户购买行为的商品折扣率尚未受到充分关注。本文提出折扣感知网络（DANet），建模商品折扣率与CVR的关系。DANet包含三部分：1）时间-频率变换模块，利用傅里叶变换提取商品折扣率的频谱特征，捕捉长期趋势；2）分布去偏模块，缓解因不同购买组合及促销活动导致的用户级折扣率偏差，以及平台促销周期带来的周期性偏差；3）监督回归辅助任务，建立显式的商品折扣标签，提升模型对折扣率表征的准确性。在真实数据集上的实验表明，DANet离线AUC提升1.61%，线上A/B测试显示其在pCVR上提升3.63%，GMV提升2.23%。该模型已成功部署于阿里巴巴天猫APP。代码已公开于https://github.com/tangrc/DANet。
原文摘要 · Abstract (English)
Post-click conversion rate (CVR) is a crucial element in online recommendation systems, which addresses significant challenges such as data sparsity (DS), sample selection bias (SSB), and delayed feedback. However, the impact of item discount rate-a key factor influencing both pricing and user purchasing behavior, has received limited attention. In this paper, we introduce the Discount-Aware Network (DANet) to model the relationship between item discount rates and CVR. DANet comprises three main components: 1) a time-frequency transformation module that utilizes Fourier transform to derive the frequency spectrum and capture the long-term discount rate trends of items; 2) a distribution de-bias module designed to mitigate the biases in user-specific discount rates caused by various purchase combinations and promotional activities, as well as periodic deviations linked to different promotion periods on e-commerce platforms; and 3) a supervised regression auxiliary task that establishes the explicit item discount labels to enhance the model's performance in terms of value accuracy, facilitating an effective representation of item discount rates. Experimental results on real datasets demonstrate the superiority of DANet, with offline AUC improving by 1.61%, and online A/B test also shows that DANet achieves impressive gains of 3.63% on pCVR and 2.23% on GMV. DANet has been successfully deployed on Alibaba Tmall APP. The code is available at https://github.com/tangrc/DANet.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。