Turkish Red Crescent · Evreka
save 20 hours a month — Operational planning time
Vendor-reportedPublic sector · Logistics · Classical ML · Scaled
Logistics
GreenRoute Logistics · iHux
Vendor-reportedLogistics & transportGCC regionIn productionEnterpriseClassical ML
Vendor-reported. The customer is named and the numbers are quoted from the source page, but the account comes from the vendor. No independent confirmation.
Reported by ihux.co (vendor self-report). Checked against the source page on 2026-09-06. 5 of 5 figures below appear on that page word for word.
The problem
Manual route planning for 15,000+ daily deliveries was suboptimal, leading to late deliveries, high fuel costs, and frustrated drivers, compounded by unique GCC challenges.
What was deployed
- Vendor
- iHux
- Products
- Python ML service, Flutter mobile app, Next.js web dashboard, Google OR-Tools
- Models
- gradient-boosted model
- Technique
- Classical ML
- Build or buy
- Built in-house or to order
- Deployment
- Custom build
- Data used
- 6 months of GreenRoute historical delivery data
- Scale
- 15,000+ daily deliveries across 200 drivers
What changed
Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.
32 minutesaverage delivery timefrom 45 minutes between stopsAfter 3 months in production
“average delivery time reduced by 28% (from 45 minutes between stops to 32 minutes)”
Quoted word for word from the source
fuel costsAfter 3 months in production
“fuel costs down 19% across the fleet”
Quoted word for word from the source
96%on-time delivery ratefrom 82%After 3 months in production
“on-time delivery rate improved from 82% to 96%”
Quoted word for word from the source
15 minutesmorning route planning timefrom 3 hoursAfter 3 months in production
“morning route planning time reduced from 3 hours to 15 minutes”
Quoted word for word from the source
Driver retentionin the first quarter
“Driver retention improved by 22% in the first quarter”
Quoted word for word from the source
Difficulties and limits
- Extreme heat requiring cold-chain compliance for temperature-sensitive goods
- Gated communities with restricted access hours
- New developments not yet mapped on Google Maps
- Traffic patterns shifting dramatically during Ramadan and holiday periods
Sources
- ihux.co — vendor self-report
Similar deployments
Galo Logistics · HappyFleet
120+ — applicants contacted from one job posting
Vendor-reportedLogistics & transport · HR & recruiting · NLP · In production
Evri · Robiquity
£9m — annualised cost savings
Vendor-reportedLogistics & transport · Process automation · Other · Scaled
NJ TRANSIT · Replicant
12,000 — calls automated
Vendor-reportedLogistics & transport · Customer support · NLP · Scaled
SF Technology · HAMi
37 cards — GPU cards saved for large model inference services
Vendor-reportedLogistics & transport · Other · LLM · In production
Southeastern · UP3
80 — digital customer interactions handled by Virtual Agent
Vendor-reportedLogistics & transport · Customer support · NLP · Scaled · 2023