What challenges did Nordic Aviation Capital face before AI implementation?

Manual review of aircraft maintenance records was time-consuming, error-prone, and costly, taking up to a week per maintenance package. The extensive and unstructured nature of the documents, often thousands of pages in various formats, made automation difficult. Reducing operational costs and improving process speeds were key objectives.

What was the impact of the AI solution?

Document review time was reduced from about a week to minutes, enabling faster leasing operations. Annual cost savings estimated at approximately EUR 200,000 due to reduced dependency on manual labor and contractors. Improved accuracy and operational efficiency, supporting NAC's technical and commercial innovation goals.

Source

Nordic Aviation Capital uses Amazon Rekognition to streamline aircraft maintenance document review

Use case typeIntelligent document processingUpdated Jun 13, 2026

Nordic Aviation Capital (NAC), a leading regional aircraft lessor, automated the review of extensive and unstructured aircraft maintenance documents using Amazon Rekognition Custom Labels. The AI solution precisely identifies critical documents requiring specialist review, greatly reducing reliance on external contractors and accelerating the leasing process. The custom computer vision model was trained on only a few hundred examples, achieving over 99% recall accuracy after iterative refinement.

Organization: Nordic Aviation Capital
Industry: Manufacturing
Location: Denmark
Published: April 2022

Reported outcomes

Strategic outcomes

Speed & agilityAccelerated maintenance document reviewCost efficiencyReduced reliance on manual laborNew product / capabilityAutomated document identification workflowBetter decisions & insightImproved review accuracy and efficiency

Primary read

Use case focus

Showing 3 of 3

1Document Processing
2Computer Vision
3Operational Efficiency

Manual review of aircraft maintenance records was time-consuming, error-prone, and costly, taking up to a week per maintenance package.
The extensive and unstructured nature of the documents, often thousands of pages in various formats, made automation difficult.
Reducing operational costs and improving process speeds were key objectives.

Implemented a custom computer vision solution using Amazon Rekognition Custom Labels for image classification and document identification.
Used Amazon S3 for storing training data and leveraged Rekognition's automatic labeling features to reduce the manual effort in model training.
Iteratively improved model performance by adding challenging examples, achieving recall above 99%, far exceeding the minimum business baseline.

Technologies

Amazon Rekognition Custom Labels Amazon S3

Document review time was reduced from about a week to minutes, enabling faster leasing operations.
Annual cost savings estimated at approximately EUR 200,000 due to reduced dependency on manual labor and contractors.
Improved accuracy and operational efficiency, supporting NAC's technical and commercial innovation goals.

Sources & evidence1

Groundedness: 5/5

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence