Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Enqiang, Qiu, Yiming, Bai, Junyang, Zhang, Ping, Miao, Dadong, Wang, Songlin, Tang, Guoyu, Liu, Lin, Li, Mingming
Format:	Preprint
Published:	2024
Subjects:	Information Retrieval Machine Learning H.3.3
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866910571673157632
author	Xu, Enqiang Qiu, Yiming Bai, Junyang Zhang, Ping Miao, Dadong Wang, Songlin Tang, Guoyu Liu, Lin Li, Mingming
author_facet	Xu, Enqiang Qiu, Yiming Bai, Junyang Zhang, Ping Miao, Dadong Wang, Songlin Tang, Guoyu Liu, Lin Li, Mingming
contents	In large e-commerce platforms, search systems are typically composed of a series of modules, including recall, pre-ranking, and ranking phases. The pre-ranking phase, serving as a lightweight module, is crucial for filtering out the bulk of products in advance for the downstream ranking module. Industrial efforts on optimizing the pre-ranking model have predominantly focused on enhancing ranking consistency, model structure, and generalization towards long-tail items. Beyond these optimizations, meeting the system performance requirements presents a significant challenge. Contrasting with existing industry works, we propose a novel method: a Generalizable and RAnk-ConsistEnt Pre-Ranking Model (GRACE), which achieves: 1) Ranking consistency by introducing multiple binary classification tasks that predict whether a product is within the top-k results as estimated by the ranking model, which facilitates the addition of learning objectives on common point-wise ranking models; 2) Generalizability through contrastive learning of representation for all products by pre-training on a subset of ranking product embeddings; 3) Ease of implementation in feature construction and online deployment. Our extensive experiments demonstrate significant improvements in both offline metrics and online A/B test: a 0.75% increase in AUC and a 1.28% increase in CVR.
format	Preprint
id	arxiv_https___arxiv_org_abs_2405_05606
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model Xu, Enqiang Qiu, Yiming Bai, Junyang Zhang, Ping Miao, Dadong Wang, Songlin Tang, Guoyu Liu, Lin Li, Mingming Information Retrieval Machine Learning H.3.3 In large e-commerce platforms, search systems are typically composed of a series of modules, including recall, pre-ranking, and ranking phases. The pre-ranking phase, serving as a lightweight module, is crucial for filtering out the bulk of products in advance for the downstream ranking module. Industrial efforts on optimizing the pre-ranking model have predominantly focused on enhancing ranking consistency, model structure, and generalization towards long-tail items. Beyond these optimizations, meeting the system performance requirements presents a significant challenge. Contrasting with existing industry works, we propose a novel method: a Generalizable and RAnk-ConsistEnt Pre-Ranking Model (GRACE), which achieves: 1) Ranking consistency by introducing multiple binary classification tasks that predict whether a product is within the top-k results as estimated by the ranking model, which facilitates the addition of learning objectives on common point-wise ranking models; 2) Generalizability through contrastive learning of representation for all products by pre-training on a subset of ranking product embeddings; 3) Ease of implementation in feature construction and online deployment. Our extensive experiments demonstrate significant improvements in both offline metrics and online A/B test: a 0.75% increase in AUC and a 1.28% increase in CVR.
title	Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model
topic	Information Retrieval Machine Learning H.3.3
url	https://arxiv.org/abs/2405.05606