Deborah Okoli, a Nigerian PhD student in Applied Mathematics at Mississippi State University, had developed a simple machine learning system for online marketplaces.
In a Tuesday interview with The PUNCH, she stated that her research focuses on assisting companies and policymakers in making more informed decisions based on data in the rapidly evolving e-commerce industry.
“My goal is simple: to build machine learning models that leaders can question and trust, models that don’t just give answers, but explain how they got there,” she said.
Okoli’s research focuses on “lag-aware machine learning”
Okoli’s research focuses on a technique she refers to as “lag-aware machine learning,” which asks what and when factors influence online market growth.
She said her research examines economic drivers like labour productivity, R&D, sales, employment, and capital investment.
According to her, she creates time-shifted features and uses models that explain the timing and magnitude of each factor’s influence instead of depending on black-box algorithms.
She said, “I work with a range of models, from regularised regressions to tree-based algorithms.”
“Then I apply explainability tools like feature attribution and partial dependence plots.”
“These techniques reveal how each variable influences the forecast and whether that impact is immediate or delayed.”
She said the model was thoroughly tested before she disclosed any results.
“I use rolling-window cross-validation to simulate real-world conditions, stability checks across time lags, and residual diagnostics to ensure the models are not missing patterns,” she explained.
“This is important to confirm that the machine learning is actually adding value and not just giving us numbers,” she added.
She says the result is a straightforward forecast with an estimated confidence range and an easy-to-understand interpretation.
Okoli maintained, “For example, a spike in productivity might mean increased online sales in the next quarter, while the effects of R&D spending may unfold more gradually. These insights empower businesses to plan inventory, adjust logistics, and make proactive digital strategy decisions.”
She also emphasised that transparency was the foundation of her work.
She explained, “Forecasts should come with seatbelts. If the outcome could change drastically due to one new data point, decision-makers need to know that up front.”
Who is Deborah Okoli
Born and raised in Nigeria, Okoli was the top student in her department and earned First-Class Honours in Industrial Mathematics from Covenant University in Ogun State.
She transferred to Mississippi State University, where she is presently working toward her PhD, after starting her graduate studies in Applied Mathematics at Tennessee Tech University.
She also graduated from the University of Hull in the United Kingdom with a Master’s in Education Research.
She develops repeatable and flexible forecasting templates that organisations can customise to their economic data at Mississippi State, where she is mentored by Professors Jason Shin from the College of Business and Kim Seongjai from the Department of Mathematical Sciences.
Considering the future, Okoli stressed that she wants to make her research more widely available.
She said, “I want to create plain-language forecasting tools for non-technical users, develop AI templates that small businesses and agencies can adopt, and push for open collaborations that raise standards for clarity and accountability in machine learning.”
“As e-commerce grows, it’s not enough to predict demand; we must understand it. When machine learning becomes easy to understand, it becomes trustworthy. And when it’s trustworthy, it becomes useful,” Okoli emphasised.