Business Challenge

To enhance customer experience and reduce turnaround time (TAT) during claim settlement, IFFCO Tokio was looking for a robust emerging technology solution that could help automate their claim assessment process and minimize human intervention.

Transformation

IBM Services collaborated with IFFCO Tokio to build and deploy an AI-based Claim Damage Assessment Tool (CDAT). CDAT leverages Cognitive Image Analytics to assess the type and extent of damage incurred to the vehicle to facilitate the claims process. Within a few minutes, the assessment and the cost are given to the customer, accepting which the customer gets paid in 15 minutes.

Results

30%

reduction in claim processing time

10%

improvement in efficiency in the claim settlement process

30%

reduction in claim processing cost

Business Challenge story

Improving customer experience

A leading general insurance company, IFFCKO-Tokio is a joint venture between Indian Farmers Fertiliser Cooperative Limited (IFFCO), the world's largest fertilizer manufacturer, and Tokio Marine Group, one of the largest insurance groups in Japan. IFFCO holds 51% share in the company and the remaining 49% is held by Tokio Marine Group. The company offers a comprehensive insurance product bouquet, including motor, health, home, and so on.

It’s the third-largest private sector player in the motor segment and is poised to further grow in the vehicle insurance market, making it a key focus for the client. It receives more than 100,000 claims per month, which are currently handled by a team of 300 SMEs, spread across multiple locations to access and approve the claims. However, as many as 30% of its customers were not satisfied with the amount assessed by the claim officers. To overcome this issue, IFFCO Tokio supplemented its model that involved claim officers with another model wherein it tied up with an agency, which further worked with the motor garages. In case of any damage to the vehicle, customers could upload photographs from the spot through a mobile app. Once the garage received the photographs, it provided the repair estimate. While this model was effective, its impact was limited because it did not cover pan-India and was not scalable.

IFFCO Tokio acknowledged that improved customer experience was critical for business growth. It decided that the assessment of claims, done either by its claim officers or by the garage, should be replaced with an AI system. It was on the lookout for a robust AI-based solution that could help assess the damage, automate the process of claim assessment, approve the claim by minimizing human intervention and improve customer experience.

 

Transformation Story

Leveraging AI to reduce claim assessment time

IBM Services worked closely with IFFCO Tokio at every stage of the 6-month project to build and deploy CDAT - Claim Damage Assessment Tool. Right from initial planning and design to implementation and go-live stage, IBM Services helped in identifying and deploying the best technology options to suit the client's business needs. IBM Services team scoped out the functionality required by the client using workshops modeled on the innovative design thinking approach.

Leveraging Cognitive Image Analytics, CDAT is an analytical model that uses Advanced Computer Vision and Deep Neural Network-based techniques to assess the type and extent of damage incurred to the vehicle. This first-of-a-kind solution in the insurance industry integrates with a mobile app and clients’ back-end systems to provide a seamless user experience.   

The customer can upload photos of the damaged part through a mobile app. The AI engine analyzes the photos and within seconds generates a list of parts that need to be repaired or replaced. These parts are then searched in the historical claims database for the average cost of repair or replacement. In a few minutes, the total cost is displayed to the customer’s mobile app. If the customer accepts the claim estimate, payment is made directly to the customer's bank account within 15 minutes.

Seema Gaur, Executive VP and Head-IT, IFFCO Tokio General Insurance adds, “Going for an AI solution for auto assessment of motor claims made sense because we had claims data for the last 17 years. We had damaged photos vis-à-vis the claim settlement sheet, and we only needed to put all this in an engine so that it could speak by itself.”

In the absence of AI, these photographs were assessed by claim officers – which was a tedious and manual job as they took a few hours to assess the damage. With the AI-based app, the list of damaged parts is generated within minutes along with the cost. It’s also now much more convenient for claim officers as they are in a better position to justify the assessment to the claimant.

Proper data input is one of the essential requirements of machine learning. To ensure that there is no error, assessment data is also analyzed manually at the back office. Discrepancies and deviations (if any) are fed back to the AI model, training it through a feedback mechanism.

Going for an AI solution for auto assessment of motor claims made sense because we had claims data for the last 17 years, we only needed to put all this in an engine so that it could speak by itself.

Seema Gaur, Executive VP & Head-IT, IFFCO Tokio General Insurance Company Limited

Results Story

Increasing customer satisfaction and driving efficiency

With IBM's AI-based analytics tool, IFFCO Tokio has transformed its claim assessment process. Claim response time has now been reduced by 10 - 12 minutes. Considering, it’s a logical way of assessment, the acceptability of claim estimates by customers has risen to over 75%. This is an important indicator of customer satisfaction.

Currently, the CDAT model is operating at over 80% accuracy. 33% of Quick Claim Settlement (QCS) for personal cars are now through AI. This will help IFFCO Tokio save operational costs over a period of time. CDAT has also improved the efficiency of the motor claims settlement process by 10% and reduced the claims processing cost by 30%.

IFFCO Tokio started with the top 30 most popular models of cars. Now, the solution covers external body parts of 50 car models. The tool has a wide spectrum of coverage, encompassing all variants and generations of these 50 car models. CDAT detects the car model, color of the car, and the extent of damage, such as dent, scratch or disorientation. It then aids in calculating the claim estimate. More car models are being added to the tool along with a plan to include commercial vehicles and two-wheelers.

Seema Gaur concludes, “We have used the system for about 2 months, and it has resulted in much better customer experience. The end-to-end claim settlement time has been reduced from 3 - 4 hours to just 15 minutes.”

Going forward, we plan to use AI for pre-inspection where break-ins occur. Moreover, we plan to bring more vehicle types, as currently AI is used only for personal cars and not for commercial vehicles and two-wheelers.

Seema Gaur, Executive VP & Head-IT, IFFCO Tokio General Insurance Company Limited

IFFCO-TOKIO-Logo

IFFCO Tokio General Insurance Company Limited

IFFCO Tokio General Insurance Company Limited is a leading private sector general insurance company. It’s a joint venture between Indian Farmers Fertiliser Cooperative Limited (IFFCO), the world's largest fertilizer manufacturer, and Tokio Marine Group, one of the largest insurance groups in Japan.

It offers a variety of uniquely customized policies covering small-scale farmers to some of India’s largest automobile manufacturers. Apart from the conventional products, it also has several niche products, including Credit Insurance, Fine Arts Insurance, P&I Insurance, and Errors and Omissions Insurance for the IT sector and more. 

Take the next step

To learn more about IBM Services, please contact your IBM representative or IBM business partner or visit: ibm.com/services

View more client stories or learn more about IBM Services