At the time of opening of savings bank account, fixed deposit, mutual fund, insurance, etc, the customer needs to submit address proof and a photograph. These documents commonly are PAN Card, Driver’s License, Aadhar Card, etc. Insurance companies have to verify each document by checking the details and finding out if the documents are fraudulent. This is a time-consuming process and requires manual reviewers. The manual reviewers can themselves not guarantee a 100% accuracy on whether a photograph or a signature is fake or in their data entry processes.

Manual Inspection

The potential customer is expected to submit these documents online. The insurance company receives these documents and passes them on to the reviewers. These reviewers have to provide feedback on whether the images provided are of good quality, contain all necessary information, or if the documents are fraudulent (digitally manipulated) in any way. If the images are verified, the data from these documents is manually entered into the companies’ databases. This process of onboarding can take around a week’s time to finish.

Inspection with Nanonets

With Nanonets, the user will get immediate feedback on if the images uploaded can be used for further review. The fraud detection process is automated as well and performs better than humans. Following the document verification, the data from these documents is extracted by state-of-the-art OCR technology and updated in the company database automatically. This reduces the time spent on customer onboarding from a few days to seconds.

The Nanonets API

Our API provides high speeds and great accuracy, enables fraud detection and drives automation for insurance companies. The Nanonets API can help the insurance companies automate the process of

1. Finding out if the document images adhere to specifications like the high resolution, full documents being visible, the upright orientation of the phone, no reflection of the flash on the screen, etc. and providing instant feedback to customers.
2. Inspecting images:
   • Finding fraudulent photographs or lacking information
   • Verifying if all the documents are uploaded in the right formats
   • Automating the manual review and data entry process by intelligently extracting fields from these images.

The Nanonets Impact

We were able to reduce the time consumed in manual review from days to seconds and reduce the costs by more than 50%. Besides reducing the time spent and the costs incurred for manual reviews, the enhancement of user experience also facilitates higher rates of customer onboardings. The insurance companies do not have to worry about the accuracy of their models or the cloud infrastructure required with Nanonets handling the errors and continuously improving models.