Forecasting Donations Across 68 Stores
Goodwill of Kentucky used Safari AI to count vehicles at the drive-thru donation lanes of its 68 stores, turning every drop-off into forecasting data.
Measured from existing drive-thru cameras
Donation volume was the hardest number to plan around.
Every store depended on donations it could not schedule. Counting cars by hand took staff away from the work, surges caught teams short-handed, and inventory piled up in some stores while others ran thin.
- Donation volume was counted by hand, if at all
- Drive-thru surges caught stores short-staffed
- Inventory was balanced across 68 stores on estimates
Every drop-off counted, in every store.
Connected to drive-thru cameras via an on-premise server
Existing cameras over each donation drive-thru fed a lightweight on-premise server Safari AI deployed, so video was processed on site.
Counted every donor vehicle
Computer vision counted vehicles entering each donation lane and how long they waited to unload, store by store and hour by hour.
Turned counts into forecasts
Daily and hourly drop-off counts fed donation forecasts, surge predictions and staffing plans across all 68 stores.
Note: Illustrative data
Better forecasts, better-staffed drop-offs.
Every donor vehicle was counted at every store's drive-thru, giving the whole network one consistent baseline.
Forecasts built on counted drop-offs showed which stores would be flooded and which would run short, so inventory moves before it piles up.
Hour-by-hour patterns showed when surges hit, so stores schedule help for the rush instead of reacting to it.
Action Center: From Insight to Action.
Measurements like these feed Safari AI's Action Center, which flags a store heading into a donation surge while there is still time to add help.
- Real-time recommendations to improve KPIs via email, SMS, robocall, mobile app, Power BI, or API.
- Recommendations grounded in your own written SOPs, not generic best practices.
See this across your own locations.
Goodwill of Kentucky forecast donations from cameras already watching its drive-thru lanes. We'll walk through which stores and lanes are the best fit for a pilot on your cameras.
