AI Case Study

Ant Financial automates vehicle damage assessment to assist automobile insurers using image recognition

Ant Financial introduced an AI image recognition system for insurers which assesses external automobile damage and sets claims amounts based on the assessment. The system uses image data which automates part of the claims assessment process.

Industry

Financial Services

Insurance

Project Overview

"The Alibaba Group financial affiliate on Tuesday rolled out an artificial intelligence-driven, image-recognition system to aid vehicle insurance claims adjustors in operating faster and more efficiently. Ant is initially offering the AI damage-assessment system only to insurers, but plans to make the product available to car owners within a year."

Reported Results

"In its rollout demonstration in Beijing, Ant pitted man against machine, with its algorithm squaring off against six experienced human claims adjusters in 12 separate cases. The machine took six seconds to assess the damage and set claim amounts for the 12 cases. The human claims adjusters took six minutes and 48 seconds to reach their conclusions. Both machine and humans judged that one of the 12 cases required further investigation... Initial reaction from insurers was positive."

Technology

Function

Operations

General Operations

Background

Automobile exterior damage claims "comprise about 60% of the 45 million private-vehicle insurance claims filed in China each years, so the AI system is expected to save insurers significant time and resources. The AI system is also aimed at making assessment of external vehicle damage more-standardized and objective, reducing the potential for human claims adjusters on the scene to be influenced by the parties involved in the accident."

Benefits

Data