Paytm Achieves User Onboarding in Minutes Using Amazon Textract

Paytm, a pioneer in digital financial services andIndia’s largest digital payments, commerce, and financial services platform, turned to Amazon Web Services (AWS) to resolve a time-consuming, manual user onboarding process that includes Know Your Customer (KYC).

By using Amazon Textract, Paytm extracts user data from images of complex identity documents with 97 percent accuracy. Once the information is captured, Amazon Textract helps to identify image noise in real time, allowing Paytm to immediately notify onsite agents to retake users’ identity document pictures when necessary, saving both parties the inconvenience of repeat visits.

The solution uses an innovative machine learning-based form of Optical Character Recognition to instantly and accurately extract text and meaningfully organize data from a variety of identity document types. Paytm thereby eliminates manual data entry, minimizing human error and shrinking the time required to successfully authenticate users from days to minutes.

Precise authentication measures ensure that users are who they claim to be. Before adopting Amazon Textract, Paytm’s KYC agents would collect users’ identification details in person, record data manually, and routinely return to verify data captured in the first instance. The manual process was time-consuming, prone to human error, and could take up to four months. 

Prakash Anand, senior lead data scientist at Paytm, says Amazon Textract has served Paytm’s rapidly growing business needs well. “We had a limited budget and short timeframe to implement a more efficient user KYC solution. We found Amazon Textract to be the best option—it was cost-effective, had a high accuracy rate, and only took an hour to roll out,” says Anand.

Developing an economical in-house solution using Amazon Textract helped Paytm to avoid investing in expensive third-party independent software solutions and achieve cost savings of up to 75 percent.

According to Manoj Kumar, senior vice president and head of data platform at Paytm, digitizing the user KYC process using Amazon Textract as part of a scalable microservices architecture,has opened new avenues for Paytm to automate data extraction.

“We’ve seen immediate success with our use of Amazon Textract. Our goal is to also develop further capabilities in our tech solution by adding facial recognition and other machine learning capabilities on OCR problems, and gradually replace existing third-party software with AWS solutions,” says Kumar.

Today, Paytm supports 24.4 million merchants and is used by millions of individuals daily to pay for utilities, groceries, movie tickets, and more. The company is on a mission to extend mainstream financial services to half a billion Indian citizens on its platform.  

To learn more, visit aws.amazon.com/financial-services/