An Embedding-Based Grocery Search Model at Instacart
This work addresses the challenge of noisy log data in grocery search for Instacart users, presenting an incremental improvement with specific gains.
The paper tackles the problem of improving e-commerce search for groceries at Instacart by developing an embedding-based model with transformer encoders, achieving a 10% relative improvement in RECALL@20 offline and 4.1% cart-adds per search and 1.5% gross merchandise value improvement online.
The key to e-commerce search is how to best utilize the large yet noisy log data. In this paper, we present our embedding-based model for grocery search at Instacart. The system learns query and product representations with a two-tower transformer-based encoder architecture. To tackle the cold-start problem, we focus on content-based features. To train the model efficiently on noisy data, we propose a self-adversarial learning method and a cascade training method. AccOn an offline human evaluation dataset, we achieve 10% relative improvement in RECALL@20, and for online A/B testing, we achieve 4.1% cart-adds per search (CAPS) and 1.5% gross merchandise value (GMV) improvement. We describe how we train and deploy the embedding based search model and give a detailed analysis of the effectiveness of our method.