The burgeoning online lending segment in India is also giving rise to a new kind of challenge on sourcing credit score data.

To solve this problem, several fintech companies are using Artificial Intelligence (AI) and Machine Learning (ML) to create alternate lending data score for more than 80 per cent of the Indian population who have no credit scores. From the place where people live to the restaurants they visit to their digital footprints on social media, ML captures it all.

Live data

Mohan Yadav, a 25-year-old software professional in Mumbai, was denied a ₹25,000 personal loan by his bank since he had no credit history.

After a quick search online, he applied for a loan from Cashe, a Mumbai-based fintech company that offers personal loans to salaried professionals who have just entered the workforce. Yadav had to fill out a form with a set of questions and undertake a psychometric test that included the kind of mobile phone he uses to his current address on Cashe’s platform.

“We collect live data. For example, if the person says he is working in a particular company in a particular location but his phone number says otherwise, then we immediately reject the application. AI and ML can also tell if the person is lying or has a genuine requirement and what his repayment capacity is. We create a Social Loan Quotient for each applicant and this also helps the applicant upgrade for bigger loans in future,” said Cashe’s founder, V Raman Kumar, adding that more than 6,000 customers come to Cashe’s platform everyday. Kumar calls this Social Loan Quoitient.

The lack of credit details has also led to the emergence of several analytics start-ups that are working on ways to develop alternate data-based lending programs to offer personal loans. These start-ups tie up with larger NBFCs to provide them with the required data that NBFCs and banks are not collecting currently.

Last year, Chennai-based NBFC Shriram City Union Finance tied up with CreditMantri, a digital credit score marketplace, to launch ScoreBuilder, an alternate data-based lending program to offer personal loans to its consumers.

According to YS Chakravarthy, Chief Operating Officer, Shriram City Union Finance, the score-builder program has seen a portfolio growth of seven times in the last 12 months, and has enabled more than 95 per cent of borrowers with no prior credit score to build a solid credit profile on the bureau.

Using alternate data provided by CreditMantri, after obtaining customer consent, Shriram provides a small ticket personal loan to these customers. When monthly repayments are made on time against this loan, the customer begins to build a credit score.

CreditVidya, a Hyderabad-based data underwriting start-up, provides credit score to first-time loan seekers and borrowers looking for personal credit. CreditVidya works with several big players such as ICICI Bank and HDFC Life, among others, to provide alternate data to people who have entered the workforce recently, those who are unbanked and do not possess any credit data.

Sanjay Sharma, MD & CEO, Aye Finance, said that for more than 40 years the Indian finance industry has been stumped by the problem of making a lending decision in the absence of business documentation and credit history.

Aye Finance’s method called Cluster-Based Credit Assessment is based on data points from industry-specific clusters collected from various sources – social, business and demographic – to arrive at a lending decision.

For example, having conducted an in-depth research on the shoe cluster of Agra, Aye has been able to assess the credit worthiness of the micro and small shoe manufacturers operating in the cluster.

Most of them do not maintain formal books of their businesses. This method has allowed Aye Finance to disburse loans to over 40,000 micro enterprises since its inception in 2014.

(This story has been modified to correct factual errors.)

Related Topics