Follow Us on Google
By Benson Michael
Imagine applying for a loan to grow your small business, but the bank only considers outdated paperwork that doesn’t reflect your current performance.
Or picture a global financial institution trying to manage billions in loans while the economy shifts at lightning speed.
These are the kinds of complex challenges that Godwin David Akhamere—a forward-thinking finance professional—is committed to solving.
Akhamere’s journey into tackling these real-world financial problems began with a strong academic foundation.
He holds a Bachelor of Science in Economics from Landmark University in Kwara, Nigeria, and dual master’s degrees, an MBA and a Master of Business Analytics, from Hult International Business School in San Francisco.
This unique blend of economics, business, and data analytics equipped him with the tools to rethink entrenched financial systems and develop innovative solutions.
One of the first issues Akhamere tackles is the outdated way banks assess creditworthiness.
Traditional lending models often rely on backward-looking metrics like past income and debt levels. Akhamere likens this to driving a car using only the rearview mirror—it fails to capture emerging financial risks in real time.
In his research paper, “Behavioral Indicators in Credit Analysis: Predicting Borrower Default Using Non-Financial Behavioral Data,” Akhamere explores how digital behavioral patterns; such as app usage frequency, payment timing consistency, and the sentiment of customer service interactions, can serve as early warning signals.
His findings are compelling: borrowers with payment timing variance above six days showed a default rate of 28.7%, compared to just 8.9% for those with consistent payments. Similarly, low digital engagement (fewer than 10 logins per month) was linked to a 32.1% default likelihood, versus 12.4% for more engaged users. Even the emotional tone in customer support messages emerged as a strong predictor of risk.
These insights could empower lenders to intervene earlier and more effectively.
Akhamere also addresses the challenge of managing large-scale credit portfolios during economic volatility. Traditional risk models often falter during crises like the COVID-19 pandemic, when defaults can spike unpredictably. In his paper, “Machine Learning-Driven Credit Portfolio Optimization: Balancing Risk, Return, and Default Correlation in Volatile Markets,” he proposes the use of machine learning algorithms to dynamically assess credit exposure and reallocate risk.
His models demonstrated improved predictive accuracy, allowing institutions to optimize returns while minimizing exposure—helping ensure resilience in uncertain times and contributing to a more stable financial system.
Another area Akhamere focuses on is the persistent funding gap for small and medium-sized enterprises (SMEs), which make up about 90% of businesses and over 50% of global employment. Despite their importance, many SMEs are denied credit due to incomplete or informal financial records.
In his work, “AI-Augmented Financial Ratio Analysis: Enhancing Credit Risk Assessment for SMEs with Non-Traditional Data,” Akhamere proposes blending traditional financial ratios with alternative data—such as online customer reviews, transactional behavior, and website activity. His models revealed that features like RFM (Recency, Frequency, Monetary) scores, sentiment analysis, and digital engagement collectively contributed over 50% of predictive power, allowing for a more nuanced and inclusive assessment of creditworthiness.
Akhamere’s research is redefining how we understand financial risk. By integrating behavioral science, machine learning, and alternative data into core financial processes, he’s building a smarter, fairer, and more adaptive financial system—one that sees people and businesses not just as numbers in a ledger, but as dynamic actors in a digital economy.
