(Image source: USAA website.)
USAA (San Antonio) and Google (Mountainview, Calif.) have announced at InsureTech Connect in Las Vegas that they have developed machine learning models that instantly predict vehicle damage from digital images, allowing for faster and more cost-efficient estimates.
The new capabilities address the stage in the claims process when appraisals are required for a damaged vehicle. The machine learning models co-developed by USAA and Google will enable automatic recommendation of damages, facilitating determination of repair cost and helping to streamline the process, according to the companies.
USAA describes the claims process powered by the new models as follows: First, images of damaged vehicles are sent to Google Cloud. The images are then analyzed by Google Cloud models in real-time, which makes damaged part predictions that are returned to USAA. Next, the predictions are sent digitally to estimating and technology solution provider Mitchell International (San Diego), whose platform maps the predicted parts to real-parts and incorporates them directly into an actual estimate. USAA appraisers then review the Mitchell estimate, and make changes as needed. The machine learning models and estimate integration help save appraisers time, and the appraiser feedback helps improve the models synergistically.
USAA reports that it has already begun to experiment with image-to-estimate through the use of drones and aerial imagery during catastrophes. The company anticipates that through the use of artificial intelligence it will continue to further streamline appraisals, enabling faster processing of claims by allowing appraisers to focus on complex cases and eventually supporting end-to-end touchless claims.
More Convenient, Cost-Effective Solutions
“The damage estimation process can be a complex, emotionally charged event, and we always aim to reduce friction and improve the member experience,” comments Ramon Lopez, VP Innovation. “The future of customer experience in insurance is more convenient, cost effective solutions, backed by machine learning and computational power.”
USAA and Google report that, in early tests, the machine learning models have been able to predict damage across a diverse vehicle set with a high degree of accuracy. USAA says it will continue to add features with the aim of unlocking the potential for end-to-end touchless claims in the future.