What does it take to know if a borrower is good for the money?

While credit scores may be the most obvious answer, there’s another simple way to assess creditworthiness: bank statements. The day-to-day transactions of a borrower can tell a lot about one’s financial health—from their income to spending patterns.

When combined with a robust underwriting strategy, bank statements can give lenders a holistic picture of borrowers’ finances. 

Transaction analysis, however, isn’t new—lenders have been assessing borrowers based on their bank statements for a while now. But thanks to digitisation, they can now be leveraged for better and more holistic underwriting.

The process is now automated, making it faster and more accurate, with zero human intervention. Today, bank statement analysis for digital lending happens in three ways:

• PDF upload: Much like the traditional submission of bank statements, borrowers are asked to upload their bank statements during their application/onboarding. These PDFs are then vetted for authenticity and transactions to determine the borrower’s creditworthiness. 
• Net banking:  Borrowers are requested to log in to their net banking account, from which bank statements are extracted for analysis.
• OTP-based consent to access borrower data from account aggregator: Thanks to RBI green-lighting the Account Aggregator framework in September 2021, bank statement analysis—and in the process, onboarding—has become a lot more efficient. Now, lenders can extract transactions of users with their consent with a simple OTP authentication.  

Decoding the financials of borrowers

Thanks to data analytics, automated bank statement analysers can assess the financial health of borrowers by classifying transactions and detecting patterns. This data can further be used in the underwriting process to determine the eligibility of customers and set price-based rates of interest.

Also Read: Is fintech in SEA changing its focus for further development?

Here are some of the metrics that can be used from transactions:

• Liabilities of the borrowers: Financial statement analysers look for bulk withdrawals, or patterns of withdrawals at regular intervals to determine the obligations of borrowers. When combined with credit scores, this can give a lender a clear picture of a borrower’s liabilities. And in new-to-credit cases, these liabilities can help lenders determine the affordability of the borrower, enabling them to extend an optimum credit amount. 
• Income: Bank statements are reliable proof of borrowers’ monthly income. Automated analysers can detect salaries and any other regular income that the borrower may have. Analysers can also check for the average bank balance each month to determine income-spending habits. 
• Merchant categorisation: Automated transaction analysis can also give lenders a clear picture of the borrower’s spending habits by categorising transactions from merchants. These categorisations can also help lenders check for the financial prudence of the borrowers. For example, timely payment of loans and utility bills.  

Apart from detecting transaction trends, analysers can also help flag malicious activity like tampered bank statements, wrong updation of statements, and more.

These analyses, while they sound like a lot of work, happen quietly in the background during onboarding and may simply take minutes, if not seconds!

The building blocks for modern, scalable lending

Thanks to deep data analytics, AI, and ML, lenders can disburse credit faster, at scale, and across contexts. And leveraging automated transaction analysis plays a crucial role in this endeavour too. Here’s how advancement in bank statement analysis has helped lenders scale their business digitally:

• Error-free decision-making: Automated bank statement analysers need zero human intervention, leaving less room for errors. Lenders can rely on these analysers for better decisions. 
• Lightning-fast speed: Transaction analysers can process statements in a matter of seconds. An efficient bank statement analyser, when integrated with a lender’s workflow, can help disburse credit to customers in minutes. 
• Optimal loan pricing: Bank statement analysers give lenders a holistic view of a borrower’s financial health, enabling lenders to categorise borrowers based on risk profiles. This helps set optimal disbursal amounts at optimal rates of interest.

Modern lending stands on speed, precision, and minimal friction. However, a lender’s core strength lies in constantly fine-tuning its underwriting models. Upgrading to automated transaction analysis is a sure-shot way to optimise and scale a credit product. 

—

Editor’s note: e27 aims to foster thought leadership by publishing views from the community. Share your opinion by submitting an article, video, podcast, or infographic

Join our e27 Telegram group, FB community, or like the e27 Facebook page

The image featured in the article has been generated utilising an AI-powered tool

The post How to enhance credit decision making with technology appeared first on e27.