In an 8-week A/B test on OTTO's live e-commerce search, a two-tower DNN with softmax cross-entropy loss achieved statistically significant gains of +1.86% clicks and +0.56% revenue over a production LambdaMART baseline, with units sold unchanged.
Towards Better Web Search Performance: Pre-training, Fine-tuning and Learning to Rank
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper describes the approach of the THUIR team at the WSDM Cup 2023 Pre-training for Web Search task. This task requires the participant to rank the relevant documents for each query. We propose a new data pre-processing method and conduct pre-training and fine-tuning with the processed data. Moreover, we extract statistical, axiomatic, and semantic features to enhance the ranking performance. After the feature extraction, diverse learning-to-rank models are employed to merge those features. The experimental results show the superiority of our proposal. We finally achieve second place in this competition.
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Industry Insights from Comparing Deep Learning and GBDT Models for E-Commerce Learning-to-Rank
In an 8-week A/B test on OTTO's live e-commerce search, a two-tower DNN with softmax cross-entropy loss achieved statistically significant gains of +1.86% clicks and +0.56% revenue over a production LambdaMART baseline, with units sold unchanged.