Customer Story

How PayU streamlined Customer Onboarding For Digital Lenders using Docsumo

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Download the Case-study

Best in class for capturing data from financial documents

“We are using Docsumo’s APIs for automating data capture from bank statements and identity cards while on-boarding customers.  It has reduced the time our operations team spends on data entry by manifolds while providing a much better customer experience.”

Prashanth Ranganathan

CEO, PayU Credit

About the customer

PayU are a multinational fintech company providing payment technology to merchants in 20 countries. They operate a digital lending platform in India, processing over 100,000 loan applications a month and disbursing over $200mn in retail loans annually.
Retail Lending
Company size
1500+ Employees
Portfolio Units
100,000+ per Month
Document Processed
$200+ Million/Year

The case study: In a nutshell


Manually scanning id & income verification documents
500+ underwriters process 100,000+ applications on a weekly process
Scanning data from 100+ bank statement types from 100+ banks manually is cumbersome
Little to no validation done on captured data
All documents had to undergo double manual entry


Capture data from unstructured documents with smart AI-based APIs
Employees review only exceptions
All the variations in layout is taken care by ML-based smart data extraction API
Docsumo's algorithms auto-classify letters and validate data with custom rules in real-time
95%+ straight through processing

The Challenge

Process unstructured id & income verification documents

  • Payu collects identity proof, address proof and income proof from each customer for onboarding.

Identify & classify documents

  • Payu needs to classify 7 different document types for each applications and queued for manual data extraction
  • Data to extract includes id and income verification details, tax, and transaction details

Capture data from bank statements with 100+ layouts from 100+ banks

  • Not only did the structures vary for different bank statements but the position of data to capture varies for these documents
  • Some of them were in tabular formats.

Categorize & derive attributes from extracted data

  • The manual extraction lacked a logical validation of payment and trasaction details.

The Docsumo Solution

Ingesting id & income verification documents

  • API-based direct integration that seamlessly ingests Bank Statements, Checks, Passport, Driving License, Voter ID, National ID (Aadhaar), and Utility Bills onto Docsumo.

Pre-processing and getting ready for data extraction

  • Inbuilt document pre-processors identified the letter formats (JPG, PDF, PNG etc.) and queued them up for data extraction.

Data extraction from unstructured text

  • Docsumo's OCR module used the vectorized position reference in a letter to extract data.
  • The OCR not only parsed through letters with varying fonts, layouts, image quality, and resolution; it even extracted data from the tables with 95%+ accuracy.

Intelligent categorization of key value pairs

  • Our proprietary NLP-based classification framework started rapidly learning from all the documents. It was trained to categorize key value pairs and line items.
  • Another algorithm started making intelligent predictions to identify the data within a letter.

Rule-based data validation

  • Once the data is extracted, a rule-based validation engine applied contextual data validation and correction algorithms.

Integration with downstream software

  • The data was extracted in a JSON format that was easily integrated into NDR's Salesforce instance via APIs and iframe.

Result: 99%+ Data extraction accuracy

Faster processing of unstructured data
Touchless processing using smart validation rules
Data accuracy with intelligent automation
Ready to automate your data extraction?
Let's talk.
Speaker Icon
Docsumo's intelligent document processing enables you to extract data easily, efficiently, and accurately.
Fill up the form to speak with an automation expert.
G2 & Capterra Ratings for Docsumo