CASHe, one of the largest digital lending application in the country, uses a new social behaviour-based credit rating system for faster lending to young millennials who may not have good CIBIL scores.
CASHe, one of the largest digital lending application in the country, uses a new social behaviour-based credit rating system for faster lending to young millennials who may not have good CIBIL scores. Names as ‘Social Loan Quotient’, the rating system uses social and media footprint, education, remuneration, career and financial history to determine the credit score of the applicant.
Is such data safe for lending? Can it be seen as a threat to personal security? Responding to these questions, Ketan Patel, Executive Director and CEO of CASHe, told FE Online, “The social behaviour based credit rating system for young salaried millennial, which is called Social Loan Quotient (SLQ), is absolutely safe and secure. SLQ is developed on algorithm-based machine learning and artificial intelligence which means there is hardly any room for human error.”
Patel said that SLQ is linked to a number of data points, including the borrowers online and offline data like his mobile number, no of Facebook friends, public interactions on social media, education, remuneration, career and social media footprint through which the scores are generated in real-time and enables the customer to know, within a few seconds, if he qualifies for a loan with CASHe or not.
“The continuous development of our algorithm has helped us correctly predict and fulfil millennial needs,” he added.
To save customer’s data, Patel sais, “As part of a multi-pronged security approach, we make sure customer data and their interactions are secured at the highest levels.”
Talking further on whether data of borrowers from social media leave the assessment very loose and allow scope for errors, Patel said, “Social Loan Quotient (SLQ) is derived from great amount of research, using big data and machine learning to ultimately build an engine that trains, learns, adapts and predicts human behaviour.”
“This mechanism uses advanced machine learning and artificial intelligence in real-time because of which there is zero error operation. It analyses unstructured data from various sources such as social media profiles, mobile data, KYC documents and identifies behavioural patterns and connections which ensures sound underwriting eventually resulting in zero errors,” he added.
WATCH VIDEO: What is Repo Linked Lending Rate, Home Loan? RLLR meaning, comparison vs MCLR
CASHe recently claimed to have cross loan disbursal over Rs 1500 crore to over 2 lakh consumers. The lender targets young millennial who opt for short personal loans to fulfil their aspirations such as buying gadgets and travelling.
“What sets CASHe apart is the fact that we do not depend on the traditional CIBIL score system to decide loan eligibility – our fully automated AI system creates an alternative credit rating system which is an industry first in this domain. The average time taken for a loan to be disbursed is about 10 minutes, subject to proper submission of all documents. CASHe offers loans from Rs 10,000 to Rs 2, 00,000 payable over 15 – 180 days,” said Patel.