CanadaLogistics and transport2019 – ongoingCanada Post
Random-forest analysis of letter-carrier injuries
Canada Post analyzed 4.9 million employee-route-day records to identify injury risk factors
Problem
Canada Post needed to understand which working conditions were associated with letter-carrier injuries. Injuries were relatively rare, creating an imbalanced classification problem.
Approach
Its analytics team used a random-forest model to examine employee and route characteristics alongside weather. The analysis identified carrier tenure, near-freezing temperatures and walking distance as important risk factors.
Results
Takeaway
The model identified risk factors for safety planning. Canada Post did not report a resulting reduction in injuries.
Categories
- Size
- Large enterprise
- Industry
- Logistics and transport
- Business function
- Human resourcesProduction and quality
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
Canada Post's analytics director presented a random-forest injury study covering 4.9 million employee-route-day records. The findings linked injury risk to tenure, temperature and walking distance without reporting a subsequent injury reduction.
Full details are in the original sources.
