fbpx

Success Story

Leveraging Robotic Process Automation to mask >500,000 national ID numbers with 98% accuracy for Pramerica life insurance

Download PDF
  • 500,000+ documents masked
  • 10 Seconds average job completion time
  • >98 % accuracy
  • 5 million+ jobs executed by bots

Challenge

Under a new data security compliance issued by the Government of India, any organization that collects national ID numbers of their customers, needs to save the information in a masked format in their database. Following this mandate, Pramerica Life Insurance (PLI) wanted to mask the existing documents that had national ID numbers of their customers mentioned for compliance. However, this task, if done manually, would have taken a lot of man-hours of effort and was highly error-prone. Pramerica thus wanted to automate this process and approached Daffodil for the same. The requirement was to mask approx. 500,000 documents stored in their database and replace the original document with the masked version.

The documents were stored online on IBM Filenet, an ECM technology (Enterprise content management) that is used by enterprises for their document management. The challenge was to download each image from the FileNet eDMS, open the image in a photo viewer application, identify the ID number in the image, mask the ID number and save the copy back to the eDMS.

Solution

Solution

Daffodil leveraged UIPath’s intelligent automation platform and developed a logic-driven utility on Windows OS for masking the ID numbers. The project started with a Proof of Concept (PoC) to evaluate the accuracy and feasibility of the solution.

UiPath bots were trained to download the unmasked image files from FileNet eDMS and open them in the Microsoft photo viewer application. One of the challenges was that a lot of image files were manually scanned and uploaded to their eDMS, hence the location of ID numbers was not consistent. In order to precisely identify the location of the ID number in the image, a different utility was developed using Google Vision API.

The custom scripts were made using Python programming language. After the project was completed, the utility was installed in desktops at Premerica’s premises to ensure secure access. 

Impact

Impact

By automating the national ID number masking using RPA, Pramerica Life Insurance was able to mask the 12-digit uID of more than 500,000 customers way before the government's deadline, which would not have been possible if the entire exercise was done manually. The average time that the utility took to mask a document was close to 10 seconds and the entire project was completed with a 98% accuracy rate.

Challenge
  • 500,000+ documents masked
  • 10 Seconds average job completion time
  • >98 % accuracy
  • 5 million+ jobs executed by bots

 

“Team Daffodil has provided excellent technical solution support in achieving project completion within restrictive timelines and in good success rate. Great support from the Daffodil IT team to the Pramerica team in overall progress.”

Gagandeep Singh Gumber, Head-IT, PLI

Read Related Case Studies

Get in Touch

Sign up for a 30 min no-obligation strategic session with us

Let us understand your business objectives, set up initial milestones, and plan your software project.

At the end of this 30 min session, walk out with:
  • Validation of your project idea/ scope of your project
  • Actionable insights on which technology would suit your requirements
  • Industry specific best practices that can be applied to your project
  • Implementation and engagement plan of action
  • Ballpark estimate and time-frame for development


    Awards & Accolades