How microfinance startups leverage AI to democratise credit access

SmartCoin uses alternate data from mobile phones and digital footprints for user onboarding and verification.

According to a global TransUnion study titled “Empowering Credit Inclusion: A Deeper Perspective on Credit Underserved and Unserved Consumers,” more than 160 million consumers were credit underserved in India at the end of 2021. The new-age lending platforms are trying to bridge this gap.

By offering micro-loans to underserved middle/lower-income segments, these platforms have simplified and increased lending in India. They are entirely digital, have instant disbursement, and lower ticket prices (as low as INR 1,000).

AI at play

Mumbai-based digital lending company CASHe uses an AI-powered social behaviour-based credit-rating system called Social Loan Quotient [SLQ] to assess the goodness quotient of the borrower and their ability to repay.

AIM Daily XO

Join our editors every weekday evening as they steer you through the most significant news of the day, introduce you to fresh perspectives, and provide unexpected moments of joy
Your newsletter subscriptions are subject to AIM Privacy Policy and Terms and Conditions.

The company caters to young working professionals who are either near-prime or subprime borrowers with or without a prior credit history. It leverages a combination of Big Data Analytics and proprietary algorithms to analyse non-traditional data derived from multiple online and offline data points, like smartphone metadata, social media footprint, education, remuneration, career, and financial history and calculate the borrower’s creditworthiness. The platform measures a borrower’s propensity to default based on their current behavioural information instead of traditional credit scoring systems that deliver a score based on historical financial behaviour. The scores are generated in real-time, enabling customers to know, within a few seconds, if they qualify for a loan with CASHe. A higher SLQ score represents a lower propensity to default. 

Recently, CASHe expanded into the wealth management space by acquiring Sqrrl, a Gurgaon-based WealthTech platform. Established in 2017, Sqrrl is a mobile-first wealth management platform focused on millennials and Gen Zs. It provides unique offerings to invest and grow their earnings without the hassle of tedious paperwork through its multiple savings and investment products. Sqrrl uses powerful data analytics and automated processes to deliver the best possible investment experience at the lowest cost.

Download our Mobile App

Bengaluru-based SmartCoin Financials leverages AI and ML algorithms to provide small-ticket loans to ensure credit access to the underbanked and underserved sections. In addition, they use AI for digitising and streamlining various operations such as delinquency prediction, and fraud detection, which includes both KYC – information extraction and face match, income prediction, SMS parsing and categorisation, collection scorecard, assisted customer support and cost optimisations.

SmartCoin uses alternate data from mobile phones and digital footprints for user onboarding and verification. For instance, the platform uses facial recognition algorithms to cross-validate the prospective borrower’s documents.

“Our proprietary AI/ML models trained over billions of alternate data points spanning transactional and behavioural attributes go beyond traditional sources to predict fraud and default risk predicting the best loan terms suitable to the user’s risk profile. Our credit scoring has consistently outperformed standard bureau scores in terms of risk assessment for various cohorts of users, especially those with little or no credit history. Furthermore, our text extraction and language and image processing engines play a vital role in building a 360-degree profile of users, which is impossible by traditional form-filling approaches,” said Rohit Garg, CEO & Co-founder, SmartCoin. “Our app also takes the user through a gamified credit ladder journey with audio-visual cues and vernacular support, allowing us to create a spectrum of personalised products.”

The company has engineered the entire loan lifecycle to make it 100 percent automated, digitised and paperless, reducing the operating costs drastically. This makes all kinds of loan customisations sustainable and the model highly scalable across segments and geographies.

“Full-stack servicing technologies have been built internally to ensure a swift, seamless experience in availing credit and support the scaling of our financial services with minimum opex. Having received the license from RBI (India’s central bank) to expand the portfolio of our financial services, we are well-positioned to become the first “neo-bank” for Emerging India,” Rohit added.

Ethical AI

“Traditional lending is prone to higher bias as a result of humans making decisions. I still remember a conference I attended back in the US where I was told people who re-joined the bank after a vacation had a higher overdue in terms of whoever they approved versus other people. That is because they were just generally in a good mood. If you think about it, that is straight-up bias right there. I think a machine-driven decision approach can give better results,” said Yashoraj , Chief Business Officer & CTO, CASHe. 

Check out: Talking Ethical AI with Yashoraj Tyagi

“All the teams are deeply focused on business objectives via the OKR framework. Our Tech Team majorly focuses on building efficiency/scalability and AUC optimisation. The Risk Team primarily focuses on model explainability, tuning thresholds for delinquency portfolio tracking that are used for bias detection while the analytics team focuses on enhancing Data quality. We systematically feed ethical principles related to AI and AI-based applications into our platform by ensuring 100% digitisation which means that no human decision-making is involved. As a result, biases can be eliminated, and fairness can be ensured by looking at the score distribution across different variables and prolonging continuous experimentation over various micro-segments,” said Rohit. 

SmartCoin is committed to protecting consumer data. “We take explicit consent from users with contextual details about how their data will be used. We ensure that every last bit of data is encrypted while in transit and while at rest. Furthermore, we also see that all CISA and ISO-27001 guidelines are followed for confirming data privacy and security,” said Rohit.

Sign up for The Deep Learning Podcast

by Vijayalakshmi Anandan

The Deep Learning Curve is a technology-based podcast hosted by Vijayalakshmi Anandan - Video Presenter and Podcaster at Analytics India Magazine. This podcast is the narrator's journey of curiosity and discovery in the world of technology.

Sri Krishna
Sri Krishna is a technology enthusiast with a professional background in journalism. He believes in writing on subjects that evoke a thought process towards a better world. When not writing, he indulges his passion for automobiles and poetry.

Our Upcoming Events

24th Mar, 2023 | Webinar
Women-in-Tech: Are you ready for the Techade

27-28th Apr, 2023 I Bangalore
Data Engineering Summit (DES) 2023

23 Jun, 2023 | Bangalore
MachineCon India 2023 [AI100 Awards]

21 Jul, 2023 | New York
MachineCon USA 2023 [AI100 Awards]

3 Ways to Join our Community

Telegram group

Discover special offers, top stories, upcoming events, and more.

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Subscribe to our Daily newsletter

Get our daily awesome stories & videos in your inbox

Council Post: Evolution of Data Science: Skillset, Toolset, and Mindset

In my opinion, there will be considerable disorder and disarray in the near future concerning the emerging fields of data and analytics. The proliferation of platforms such as ChatGPT or Bard has generated a lot of buzz. While some users are enthusiastic about the potential benefits of generative AI and its extensive use in business and daily life, others have raised concerns regarding the accuracy, ethics, and related issues.