Saved in:
Bibliographic Details
Main Authors: Kekuda, Akshay, Zhang, Yuyang, Udayashankar, Arun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.01946
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912391495680000
author Kekuda, Akshay
Zhang, Yuyang
Udayashankar, Arun
author_facet Kekuda, Akshay
Zhang, Yuyang
Udayashankar, Arun
contents In this abstract we present a series of optimizations we performed on the two-tower model architecture [14], and training and evaluation datasets to implement semantic product search at Best Buy. Search queries on bestbuy.com follow the pareto distribution whereby a minority of them account for most searches. This leaves us with a long tail of search queries that have low frequency of issuance. The queries in the long tail suffer from very spare interaction signals. Our current work focuses on building a model to serve the long tail queries. We present a series of optimizations we have done to this model to maximize conversion for the purpose of retrieval from the catalog. The first optimization we present is using a large language model to improve the sparsity of conversion signals. The second optimization is pretraining an off-the-shelf transformer-based model on the Best Buy catalog data. The third optimization we present is on the finetuning front. We use query-to-query pairs in addition to query-to-product pairs and combining the above strategies for finetuning the model. We also demonstrate how merging the weights of these finetuned models improves the evaluation metrics. Finally, we provide a recipe for curating an evaluation dataset for continuous monitoring of model performance with human-in-the-loop evaluation. We found that adding this recall mechanism to our current term match-based recall improved conversion by 3% in an online A/B test.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01946
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Embedding based retrieval for long tail search queries in ecommerce
Kekuda, Akshay
Zhang, Yuyang
Udayashankar, Arun
Information Retrieval
In this abstract we present a series of optimizations we performed on the two-tower model architecture [14], and training and evaluation datasets to implement semantic product search at Best Buy. Search queries on bestbuy.com follow the pareto distribution whereby a minority of them account for most searches. This leaves us with a long tail of search queries that have low frequency of issuance. The queries in the long tail suffer from very spare interaction signals. Our current work focuses on building a model to serve the long tail queries. We present a series of optimizations we have done to this model to maximize conversion for the purpose of retrieval from the catalog. The first optimization we present is using a large language model to improve the sparsity of conversion signals. The second optimization is pretraining an off-the-shelf transformer-based model on the Best Buy catalog data. The third optimization we present is on the finetuning front. We use query-to-query pairs in addition to query-to-product pairs and combining the above strategies for finetuning the model. We also demonstrate how merging the weights of these finetuned models improves the evaluation metrics. Finally, we provide a recipe for curating an evaluation dataset for continuous monitoring of model performance with human-in-the-loop evaluation. We found that adding this recall mechanism to our current term match-based recall improved conversion by 3% in an online A/B test.
title Embedding based retrieval for long tail search queries in ecommerce
topic Information Retrieval
url https://arxiv.org/abs/2505.01946