ecommerce_ops · workflow
Machine Learning at Shopify: product classification, fraud detection, Sidekick merchant assistant, and GMV forecasting
Shopify must optimize commerce for millions of merchants simultaneously across product metadata quality, fraud prevention, merchant guidance, capital access, and search relevance — a continuously expanding optimization problem at massive scale.
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 · Product classification and enrichment
Finetuned Qwen multimodal models classify and enrich the metadata of each product uploaded into the system.
Tools used
LLaMa modelsGCPNebiusCentMLToloka
Outcome
Shopify has multiple ML systems in production including product classification running hundreds of millions of inferences per day, fraud assessment on every transaction, a multi-purpose merchant assistant (Sidekick), vector embeddings powering search and recommendations across billions of products, and GMV forecasting for merchant capital access.
Results
Time savedhundreds of millions of inferences a day
Grounding & classification
Source type: technical build writeup
19 fields verified against source quotes, 5 dropped as unverifiable.
conversational aidocument classificationenterprise searchforecastingfraud detectionpredictive analyticsrecommendation systemproduct catalogmetric backednamed customerproduction runtime claimedecommercesoftwarethroughput increasetechnical build writeupecommerce opsfinance opsextract classify route