AI Case Study

Infinity Property & Casualty processes claims 35% faster by developing a solution to flag potentially fraudulent claims using machine learning

Infinity Property & Casualty developed a calculate the probability of a claim being fraudulent using rules and machine learning when an accident is first reported. Suspicious claims are forwarded to investigators within 1-2 days from previous 1-2 months. In one month the company was able to increase subrogation recovery by $1 million; after six months, the savings rose to $12 million. Overall claim processing time has been reduced by 35% as a result.

Industry

Professional Services

Consultancy And Business Services

Project Overview

"By using predictive analytics the company developed a process to assign different "scores" on fraud probabilities when claimants first report an accident. By using a rules engine and machine learning that automatically scores claims based on its fraud probability, suspicious claims are forwarded into investigators within a day or two from 30-60 days and with better hit rates.
In the first month of using IBM's SPSS analytics-based system, our company has been able to increase subrogation recovery by $1 million; after six months, the savings rose to $12 million."

Reported Results

35.5 percent improvement in claims processing speed

Subrogation recovery of $12m in six months

Technology

Function

Risk

Audit

Background

"Infinity Property & Casualty, a mid-size insurance businesses providing specialty insurance struggled with effective fraud management."

Benefits

Data