The AI model, which is currently 76% accurate, aims to help low-income and underbanked Nigerians access microloans ranging from ₦30,000 ($18) to ₦50,000 ($31). Lendsqr's innovation addresses a core challenge in African lending: verifying the ability and willingness to repay loans in the absence of traditional financial records.
Rethinking the 5 Cs of Lending
Traditionally, lenders assess borrowers using the “five Cs” of credit—character, capacity, capital, collateral, and conditions. For millions of Nigerians, however, proving character and capacity through pay slips, tax records, or credit history is out of reach.
Lendsqr’s CEO, Adedeji Olowe, explained the rationale behind the new model to TechCabal:
“Can we help vulnerable people prove their capacity and character, not through paperwork but through their words? That’s the thinking behind this AI project.”
How the AI Model Works
Rather than filling forms, prospective borrowers interact with the AI via video or voice. They answer simple questions about their income sources and repayment plans. The model analyzes vocal cues, facial expressions, and speech patterns to predict whether they’re likely to repay the loan.
Lendsqr is currently piloting the model using its own funds, with plans to make its research and training data open to the public by Q3 2025. Competitors and partners alike will be able to leverage it to build or enhance their lending engines.
Targeting the Underserved in Africa—and Abroad
Though its immediate goal is Nigeria’s mass market, Lendsqr also plans to test the model in Canada, supporting new immigrants and students who typically lack a credit history.
“Africa is the primary target because this is where the problem is largest,” Olowe said. “Across Africa—Kenya, Ghana, Ivory Coast, Malawi, and South Africa—you see the same pattern: the underbanked and vulnerable struggle to get loans because they lack documentation.”
Potential Economic Game Changer
If successful, this innovation could be transformative. In Nigeria, only 6% of adults have accessed formal credit, and just 12% of 41 million small businesses have any form of financing. Meanwhile, banks continue to report record deposits—funds that rarely reach the grassroots economy.
Fintechs have tried to fill the gap, but their verification systems are often costly, increasing borrowing rates. Lendsqr’s AI could drastically reduce that cost. For clients like Kredi, Snapcash, and Blockacash, the model could both lower default rates and unlock access to new borrowers.
“Imagine you’re a lender giving loans to 10,000 people: If 9,000 repay because of better screening, it dramatically improves your profitability and sustainability,” Olowe noted.
Public-Private Backing and a 90% Accuracy Goal
The AI project is backed by Google and Nigeria’s Ministry of Communications, Innovation & Digital Economy. The tool will only be released for broader adoption when it reaches 90% accuracy, according to Olowe.
“If it works, it won’t replace traditional lending for mortgages or car loans,” he said. “But it could help people access foundational credit. Small, life-changing amounts.”
If Lendsqr delivers on its promise, its AI may do more than screen borrowers—it could redefine the very structure of inclusive finance in Africa.