PortugalLogistics and transport2025 – ongoingCTT - Correios de Portugal
Tray.Vision sorting checks and Predict delivery-window forecasts
CTT said computer vision on sorting belts lifted machine productivity by about 20% and AI narrowed delivery windows for two-thirds of express parcels
Problem
CTT wanted better quality in treating parcels on its sorting machines and wanted to give customers a more precise delivery time window.
Approach
Tray.Vision combines computer vision and AI to flag problems such as dirty trays on the sorting belts. Predict uses AI to forecast delivery times so customers get a shorter delivery window. Nuno Matos, CTT's director of digital, new channels and innovation, described both in an ECO interview in November 2025. CTT did not give start dates for either project.
Results
Takeaway
A small fix on the sorting line and a forecasting model on the delivery side were both reported as measurable gains, although only by the company.
Categories
- Size
- Large enterprise
- Industry
- Logistics and transport
- Business function
- Production and quality
- Innovation type
- Process innovationProduct and service innovation
- AI technology
- Computer visionPredictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
In an interview, a CTT digital director described Tray.Vision, which pairs computer vision with AI on sorting machines, and Predict, which shortens delivery windows. He gave a productivity gain of about 20%, a two-thirds share of express deliveries covered and a confidence interval above 85%. These are the company's own figures.
Full details are in the original sources.
