简单深度模型在电商推荐中点击和收入上优于传统树模型。
Industry Insights from Comparing Deep Learning and GBDT Models for E-Commerce Learning-to-Rank
- 用简单DNN对比生产级LambdaMART模型
- 线上测试显示点击和收入提升，销量持平
- 适合关注推荐系统性能优化的工业界研究者
在电商推荐与搜索系统中，基于树的模型（如LambdaMART）是学习排序（LTR）任务的强基准。尽管其在业界广泛应用且效果显著，关于深度神经网络（DNN）能否超越传统树模型的讨论仍持续存在。为推进该议题，我们系统性地将DNN与生产级别的LambdaMART模型进行对比。在OTTO的私有数据集上评估多种DNN架构与损失函数，并通过为期8周的线上A/B测试验证结果。结果显示，一种简单的DNN架构在总点击量和总收益上优于强基线树模型，同时在总销售件数上达到相当水平。
原文摘要 · Abstract (English)
In e-commerce recommender and search systems, tree-based models, such as LambdaMART, have set a strong baseline for Learning-to-Rank (LTR) tasks. Despite their effectiveness and widespread adoption in industry, the debate continues whether deep neural networks (DNNs) can outperform traditional tree-based models in this domain. To contribute to this discussion, we systematically benchmark DNNs against our production-grade LambdaMART model. We evaluate multiple DNN architectures and loss functions on a proprietary dataset from OTTO and validate our findings through an 8-week online A/B test. The results show that a simple DNN architecture outperforms a strong tree-based baseline in terms of total clicks and revenue, while achieving parity in total units sold.
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。