AI Case Study
TensorFlight automates property inspection for underwriting, reinsurance and risk assessment with deep machine vision analysis of aerial imagery
TensorFlight uses sophisticated deep machine vision to analyse satellite, aerial, drone and street view imagery of properties. This saves substantial time and cost of in-personal property inspection which has wide value in the underwriting, reinsurance and risk assessment industries.
Industry
Financial Services
Insurance
Project Overview
"TensorFlight helps insurance companies automatically analyse imagery to help make the process of evaluating imagery more efficient. For example, identify commercial buildings in imagery or residential footprints. This is important in use cases for:
1. Underwriting: Automatically pre-fill a quote such as square footage of the roof. Highlight areas to investigate for an underwriter that might be caused by potential building degradation.
2. Reinsurance: Get more detailed information about each property in a reinsurance policy or gain alpha while trading cat bonds.
3. Risk: Better understand exposure of your portfolio or monitor transient risks.
4. Claims: Automatically resolve simple claims such as a few tiles missing from the roof. Prioritize adjuster activity after a catastrophe like a hurricane."
Reported Results
Significant time, cost and speed savings are claimed.
Technology
Likely very sophisticated use of deep learning and convolutional neural networks.
Function
Operations
Field Services
Background
The insurance industry requires significant property inspection which is an expensive and slow proposition.
Benefits
Data
Satellite, aerial and drone imagery.