Industry Insights from Comparing Deep Learning and GBDT Models for E-Commerce Learning-to-Rank
This addresses the practical problem of optimizing ranking models for e-commerce platforms, providing incremental insights for industry practitioners.
The study compared deep neural networks (DNNs) to a production-grade LambdaMART model for e-commerce learning-to-rank, finding that a simple DNN outperformed the tree-based baseline in clicks and revenue while matching it in units sold.
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.