The Challenge
A global shipping and logistics company with trucking and airline operations was hemorrhaging money on inefficient cargo loading. Trucks and aircraft were leaving facilities at just 72% capacity on average—meaning they were essentially paying to ship air on nearly a third of every route.
The problem wasn't laziness or bad intentions. Operations teams simply had no visibility into real-time capacity data. Loading decisions were made based on gut instinct and outdated spreadsheets. There was no integration between booking systems, warehouse management, and route planning. The result: millions in wasted fuel, labor, and equipment costs every year.
Our Approach
We started with a full diagnostic of their data landscape. What we found was typical of large logistics operations: critical data trapped in disconnected systems, manual processes bridging the gaps, and no single source of truth for capacity planning.
The fix required building an entirely new data infrastructure from scratch—not just dashboards, but the plumbing underneath.
The Solution
Over six months, we architected and deployed an end-to-end capacity optimization platform:
Data Integration Layer
- Connected web-based booking systems, warehouse management, and route planning tools
- Built custom integrations using Python to pull data from legacy systems
- Established real-time data flows using AWS Lambda and EventBridge
Analytics Infrastructure
- Deployed Amazon S3 for centralized data lake storage
- Built transformation pipelines in Databricks
- Created optimization algorithms in Python to recommend optimal load configurations
Operational Tools
- Developed Power BI dashboards for operations teams to monitor capacity in real-time
- Created documentation and recommendations that enabled ops leadership to issue an RFP for route optimization with carriers
- Built incentive tracking to align operational behavior with capacity goals
The Results
The impact was immediate and measurable. Capacity utilization jumped from 72% to 96%—approaching the theoretical maximum for mixed cargo operations.
First Year Impact:
- $12 million saved in cargo costs
- $7 million saved in linehaul costs
- $19 million total annual savings
We're now in Phase 2 of the engagement, with projected additional savings of $3 million in 2026 through further route optimization and carrier negotiations.
This project proved that the biggest efficiency gains often come not from new technology, but from finally connecting the data that was there all along.