On Application of Learning to Rank for E-Commerce Search

Abstract

E-Commerce (E-Com) search is an emerging important new application of information retrieval. Learning to Rank (LETOR) is a general effective strategy for optimizing search engines, and is thus also a key technology for E-Com search. While the use of LETOR for web search has been well studied, its use for E-Com search has not yet been well explored. In this paper, we discuss the practical challenges in applying learning to rank methods to E-Com search, including the challenges in feature representation, obtaining reliable relevance judgments, and optimally exploiting multiple user feedback signals such as click rates, add-to-cart ratios, order rates, and revenue. We study these new challenges using experiments on industry data sets and report several interesting findings that can provide guidance on how to optimally apply LETOR to E-Com search: First, popularity-based features defined solely on product items are very useful and LETOR methods were able to effectively optimize their combination with relevance-based features. Second, query attribute sparsity raises challenges for LETOR, and selecting features to reduce/avoid sparsity is beneficial. Third, while crowdsourcing is often useful for obtaining relevance judgments for Web search, it does not work as well for E-Com search due to difficulty in eliciting sufficiently fine grained relevance judgments. Finally, among the multiple feedback signals, the order rate is found to be the most robust training objective, followed by click rate, while add-to-cart ratio seems least robust, suggesting that an effective practical strategy may be to initially use click rates for training and gradually shift to using order rates as they become available.

References in corpus (2)

• Introducing LETOR 4.0 Datasets
• Learning Latent Vector Spaces for Product Search

Cited by in corpus (29)

• Applying Deep Learning To Airbnb Search
• Differentiable Unbiased Online Learning to Rank
• Conversational Product Search Based on Negative Feedback
• A Zero Attention Model for Personalized Product Search
• A Transformer-based Embedding Model for Personalized Product Search
• Ranking for Relevance and Display Preferences in Complex Presentation Layouts
• Learning a Fine-Grained Review-based Transformer Model for Personalized Product Search
• U-rank: Utility-oriented Learning to Rank with Implicit Feedback
• Model-agnostic vs. Model-intrinsic Interpretability for Explainable Product Search
• RankFormer: Listwise Learning-to-Rank Using Listwide Labels
• Learning to Ask: Conversational Product Search via Representation Learning
• Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning
• BubbleRank: Safe Online Learning to Re-Rank via Implicit Click Feedback
• User Response Prediction in Online Advertising
• Neural IR Meets Graph Embedding: A Ranking Model for Product Search
• A Study of Context Dependencies in Multi-page Product Search
• Learning from User Interactions with Rankings: A Unification of the Field
• Explainable Product Search with a Dynamic Relation Embedding Model
• On Gradient Boosted Decision Trees and Neural Rankers: A Case-Study on Short-Video Recommendations at ShareChat
• A Comparison of Supervised Learning to Match Methods for Product Search
• Intent term selection and refinement in e-commerce queries
• Leverage Implicit Feedback for Context-aware Product Search
• Handling Position Bias for Unbiased Learning to Rank in Hotels Search
• Learning to Rank Broad and Narrow Queries in E-Commerce
• Industry Insights from Comparing Deep Learning and GBDT Models for E-Commerce Learning-to-Rank
• A Domain Generalization Perspective on Listwise Context Modeling
• MOHPER: Multi-objective Hyperparameter Optimization Framework for E-commerce Retrieval System
• Searching Personal Collections
• AMinerGNN: Heterogeneous Graph Neural Network for Paper Click-through Rate Prediction with Fusion Query