Machine learning models reveal geographic data improves insurance claim predictions

Researchers have developed a method to incorporate geographic information into motor insurance claim prediction models, even with limited location data. By utilizing environmental data from OpenStreetMap and CORINE Land Cover, along with visual features from satellite imagery, they enhanced the accuracy of zone-level claim frequency models. The study found that combining coordinates with environmental features at a 5 km scale was most beneficial for both linear and tree-based models, demonstrating that the representation of geographic context is more crucial than model complexity. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Demonstrates how alternative data sources can improve actuarial models, potentially leading to more accurate risk assessments in insurance.

RANK_REASON Academic paper on applying machine learning to insurance risk modeling.

Read on arXiv stat.ML →

• arXiv
• OpenStreetMap
• CORINE Land Cover
• BeMTPL97
• GLM
• convolutional neural networks
• vision-transformer

• paper
• other