Frandulent claims are the bane of insurance companies. But how can one know if a case is not real? Driven by a bid to stem finanicial loss due to fake claims, India-based insurance firm IFFCO-Tokio General Insurance turned to artificial intelligence (AI) to help detect such cases.
It has developed AI solutions to spot potential fraud cases involving motor and health claims and expects to save US$1 million a year.
IFFCO-Tokio is a joint venture between Indian Farmers Fertilizer Co-operative, the world’s largest co-operative reaching more than 50 million Indian farmers, and Tokio Marine Group, the largest property and casualty insurance group in Japan.
With a wide range of insurance products and 10 million customers across India, it is no wonder that having a solution against frauds is vital for business success.
IFFCO-Tokio receives more than 2,000 motor claims daily that are processed at 12 claim service centres by around 100 claim officers. As a result of the time-consuming and demanding process, claim officers often do not have the time to pay much attention to every case to check against possible fraud.
The solution was to tap the power of AI to do the analysing of each claim. That same solution can then be adapted to other products, such as health insurance, which face similar challenges.
Turning to AI
A decision was made to use H2O.ai’s automated machine learning with pre-built algorithms. Using the platform, the AI model rates each claim with a score of between zero and one, with one being a higher probability of fraud.
With the system flagging such cases instantly and with greater accuracy, the claims processing team can pay greater attention to cases with higher scores.
Following the successful deployment of the fraud prediction model for motor insurance claims in July 2021, the company then created another model to analyze, detect and predict health insurance claims.
From the moment a patient is admitted to the point of discharge, there are many triggering points for health insurance fraud ranging from medically unnecessary services to overcharging for over-prescription of medicine.
Time and cost savings
Based on more than 100 confirmed fraudulent claims detected each month so far, IFFCO-Tokio expects to save around US$1 million annually from fake motor and health insurance claims.
Additionally, its claims officers can now focus on following up on possible fraud cases flagged by the system instead of analysing every single claim, resulting in faster processing time for genuine claims
“H2O AI Cloud is a platform that my team can learn by themselves. I find the platform to be very friendly for people who are not data scientists or have little knowledge of data science,” said Seema Gaur, Chief Information Officer and Head of IT of IFFCO-Tokio.
“This is the beginning of the usage of AI and machine learning for our company. We hope to make more use of it in the long run,” she added.