Dev.to
6/18/2026
![[System Design] Part 4 — Amazon CONDOR & Anticipatory Shipping](https://media2.dev.to/dynamic/image/width=1200,height=627,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fcr7y22086qgqejku95th.png)
[System Design] Part 4 — Amazon CONDOR & Anticipatory Shipping
Short summary
Amazon's fulfillment network uses three-tier optimization: Anticipatory Shipping (ML predicts demand weeks ahead, pre-positions inventory to local hubs), Regionalization (8 US autonomous regions reduced travel distance 60%), and CONDOR (continuous re-routing within a 5-6 hour pre-fulfillment window). CONDOR solves Prize Collecting Vehicle Routing Problem to maximize on-time delivery while minimizing transport cost.
- •Anticipatory Shipping: ML predicts regional demand 3+ days ahead, moves inventory before orders placed
- •Regionalization: 8 autonomous US regions cut avg travel distance per package by 60%
- •CONDOR: Continuous optimization engine re-evaluates routing every 15 minutes during 5-6 hour fulfillment window
Generated with AI, which can make mistakes.
Is this a good recommendation for you?



