ecommerce_ops · workflow
Shopify's machine learning playbook: scaling from order fraud detection to hundreds of products
Shopify's rule-based order fraud detection had a high false positive rate, forcing merchants to manually investigate flagged orders and causing them to cancel legitimate sales.
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 · Order placed at checkout
An order placed at checkout triggers real-time fraud evaluation before fulfillment.
Tools used
TrinoRuby on Rails
Outcome
The ML fraud detection model beat the baseline and now processes millions of orders a day; the same approach was extended to hundreds of other Shopify products including Shopify Capital, product categorization, and Help Center search.
What failed first
The existing rule-based fraud system flagged orders whenever billing and shipping addresses differed, generating excessive false positives and prompting merchants to cancel valid orders.
Grounding & classification
Source type: technical build writeup
21 fields verified against source quotes.
fraud detectionpredictive analyticspurchase orderfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareerror reductionthroughput increasetechnical build writeupecommerce opsfinance opsextract classify routemonitor detect alert