Built using medical research, lifestyle and demographics data
50 Million Lives
1.5 Million Claims
250 + Medical Studies
1 Million Faces Analysed
80% Improve in Underwriting Efficiency
FEDO SOLUTION
Fedo leveraged its proprietary cloud based risk classification models for the task. Fedo’s risk classification models generate decisions per industry standards. Fedo customized its models for the insurer based on the product, plan and sum assured and exposed an API that allowed the customer to generate decisions both real time and in batch mode.
BUSINESS IMPACT
Fedo processed 10923 cases in 1 hour with an accuracy rate of 97% as compared to a manual processing rate of 15 cases per underwriter per day.
VALUE ADD
Fedo’s analytics platform demonstrated unusual policy sales to the insurer and recommended further investigation of those cases.
70% Improvement in Policy Issuance In Turnaround Time
FEDO SOLUTION
Fedo architected an API driven digital solution for the customer that enables end customers to:
- Fill out proposal information online
- Get immediate policy decisions from Fedo’s Underwriting engine
- Book appointments for Tele Verification or Pre Policy Medical Check-ups (PPMC)
- Get the result of the tele verification / PPMC results directly through a portal
In addition, Fedo implemented a Work Bench for the insurer that had the following features:
- Automated feed of Tele Verification and PPMC results to the underwriting engine using APIs
- Recommended underwriting decisions based on Tele Verification / PPMC values
- Automate case routing system to route cases to underwriters based on load, specialty
BUSINESS IMPACT
With Fedo’s digital solution, the customer was able to accomplish an average TAT < 5 days as compared to industry standard of 7 - 8 days
VALUE ADD
Fedo’s case routing system and advanced analytics engine allowed the insurer to track underwriter productivity and identify & resolve gaps in the workflow
50% Reduction in Pre Policy Medical Check-ups
FEDO SOLUTION
The solution involved back testing past proposals using Clustering, Classification, Claims Propensity models of Fedo’s Underwriting platform. Fedo generated 12 clusters of customers based on their health risk. A classification model was then used to predict the chances of a customer claiming in the next 4 years basis. The results from the classification model were then used to identify customers who would need a medical examination and customers who do not need a detailed medical examination.
BUSINESS IMPACT
Straight Through Pass rate increased by 26% All cases newly identified as straight through pass did not have any adverse findings from medical tests.