By Onilede Titi Faith
Deborah Okoli, a Nigerian PhD student in Applied Mathematics at Mississippi State University, has developed a transparent machine learning model designed to make e-commerce forecasting more reliable for businesses and policymakers.
Okoli said her research focuses on “lag-aware” machine learning, which not only identifies economic drivers such as productivity, R&D, sales, and employment but also shows the timing of their impact.
“My goal is to build models leaders can question and trust; models that don’t just give answers but explain how they got there,” she said.
Unlike traditional “black-box” AI, her system applies explainability tools like feature attribution and partial dependence plots to reveal how each factor influences forecasts.
She stressed that accountability in AI forecasting is key: “Forecasts should come with seatbelts.”
Okoli, a First-Class graduate of Covenant University, has also studied at Tennessee Tech University and the University of Hull, UK.
At Mississippi State, she works with Professors Kim Seongjai and Jason Shin to develop forecasting templates adaptable to real-world data.
