Kenyan banks are increasingly adopting artificial intelligence (AI) technologies to identify potential loan defaulters before they miss payments. Traditionally, lenders relied on payslips, credit histories, and collateral to assess loan eligibility. However, AI now enables continuous monitoring of borrowers’ financial health beyond initial approval.

According to the Central Bank of Kenya (CBK), non-performing loans (NPLs) in the banking sector increased by Sh21 billion in the first quarter of 2026, rising from Sh674.4 billion in December 2025 to Sh695.4 billion by March 2026. This pushed the default ratio to 15.6%, reflecting ongoing financial strains despite lower interest rates.

AI Enhances Risk Assessment

AI tools such as machine learning and natural language processing analyze vast data points—including mobile money transactions, utility payments, and merchant activities—to build comprehensive borrower profiles. This approach improves creditworthiness evaluations, especially for informal workers and small businesses lacking traditional credit records.

David Mukaru, CEO of Caritas Microfinance Bank, highlighted the role of AI and data analytics in tackling non-performing loans. Banks categorize borrowers by risk levels using AI models trained to detect patterns and predict financial difficulties early.

Early Warning and Customer Engagement

AI systems serve as early warning mechanisms by tracking changes in income, delayed payments, and sector-specific stress indicators. This allows lenders to proactively engage customers with tailored solutions such as repayment restructuring or temporary relief.

Julius Kamau, Absa Bank’s Chief Operating and Digital Officer, noted that customers increasingly demand personalized banking products, a trend driving investments in AI and data science.

Human Oversight Remains Crucial

Despite AI’s growing role, final lending decisions remain with human officers to prevent algorithmic biases and ensure fairness. Concerns persist that automated systems might unfairly disadvantage borrowers from informal sectors or marginalized communities.