ecommerce_ops · ecommerce · workflow

Instacart builds a BERT-based contextual sequence retrieval system for in-session product recommendations

Instacart's recommendation surfaces relied on a disparate set of ad-hoc retrieval systems using product co-occurrence, similarity, and popularity signals, without leveraging in-session contextual sequence information from users.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · In-session user action trigger
The contextual retrieval system reacts in real time to user actions within a shopping session.
Tools used
BERTMasked Language ModelingXLNet
Outcome

The unified BERT-like contextual retrieval system delivered a 30% lift in user cart additions at launch and outsized impact across transaction volume and ad marketplace metrics, while allowing legacy systems to be deprecated.

What failed first

Legacy per-surface retrieval systems failed to use sequential context from user sessions, relied on ad-hoc co-occurrence and popularity signals, and increased maintenance burden by requiring separate systems for ads and organic surfaces.

Results
Volume30%
Source

https://tech.instacart.com/sequence-models-for-contextual-recommendations-at-instacart-93414a28e70c

How we source this →

Grounding & classification
Source type: technical build writeup
24 fields verified against source quotes.
personalizationpredictive analyticsrecommendation systemproduct catalogfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommerceaccuracy improvementconversion increasethroughput increasetechnical build writeupecommerce opsmarketing opsextract classify route