A unified Neural Network Approach to E-CommerceRelevance Learning

TL;DR

This paper introduces a scalable neural network model for relevance scoring in e-commerce search, leveraging minimal features and feedback data, outperforming traditional models and existing deep-learning baselines.

Contribution

The paper presents a novel neural network architecture with enhancements like Siamese structure and co-training, achieving superior relevance scoring with fewer features compared to GBDT models.

Findings

Significant improvement over GBDT baseline

Outperforms several off-the-shelf deep-learning models

Requires fewer features than traditional models

Abstract

Result relevance scoring is critical to e-commerce search user experience. Traditional information retrieval methods focus on keyword matching and hand-crafted or counting-based numeric features, with limited understanding of item semantic relevance. We describe a highly-scalable feed-forward neural model to provide relevance score for (query, item) pairs, using only user query and item title as features, and both user click feedback as well as limited human ratings as labels. Several general enhancements were applied to further optimize eval/test metrics, including Siamese pairwise architecture, random batch negative co-training, and point-wise fine-tuning. We found significant improvement over GBDT baseline as well as several off-the-shelf deep-learning baselines on an independently constructed ratings dataset. The GBDT model relies on 10 times more features. We also present metrics for select subset combinations of techniques mentioned above.