{"ID":2889601,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.20753","arxiv_id":"2507.20753","title":"Industry Insights from Comparing Deep Learning and GBDT Models for E-Commerce Learning-to-Rank","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2507.20753","url_pdf":"https://arxiv.org/pdf/2507.20753v1","authors":"[\"Yunus Lutz\",\"Timo Wilm\",\"Philipp Duwe\"]","published":"2025-07-28T12:02:02Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}