# Embedding based retrieval for long tail search queries in ecommerce

arXiv: https://arxiv.org/abs/2505.01946 · HTML: https://mlsanity.com/paper/2505.01946/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2025.

## Built on by (most cited first, 3 of 3)

- [Embedding-based Retrieval in Multimodal Content Moderation](https://mlsanity.com/paper/2507.01066/) (2025)
- [Beyond Retrieval-Ranking: A Multi-Agent Cognitive Decision Framework for E-Commerce Search](https://mlsanity.com/paper/2510.20567/) (2025)
- [Probe-then-Plan: Environment-Aware Planning for Industrial E-commerce Search](https://mlsanity.com/paper/2603.15262/) (2026)

## Abstract (arXiv)

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.