September 18, 2026 by Alao Abiodun | Senior Reporter
Researcher develops machine learning models for real-time decisions
A Nigerian researcher and data analytics professional, Michael Ehiedu Usiagwu, has explored how advanced machine learning models can help organisations make faster and more accurate decisions when dealing with rapidly changing data.
Usiagwu, who is based in Manchester, United Kingdom, conducted the research with Mayowa Timothy Adesina of Kansas State University, United States, and Johnson Chinonso of Kwara State Polytechnic, Nigeria.
The study, titled Advanced Machine Learning Models for Real-Time Decision Making in Dynamic Data Environments, was published in the 2025 edition of the International Journal of Science and Research Archive.
Usiagwu, the corresponding author of the study, is affiliated with the Department of Marketing, Salford University, Manchester, and the Department of Accounting, National Open University of Nigeria.
His research focuses on the use of machine learning to address the challenges organisations face when processing large volumes of data generated continuously from different sources.
According to the researchers, the rapid growth of big data and Internet of Things technologies has created environments where data is generated in large volumes and at high speed, making traditional decision-making systems increasingly inadequate.
They stated that “traditional decision-making frameworks, which rely on static models or manual analysis, are increasingly insufficient and ineffective” in dealing with continuously changing data.
The researchers therefore examined the use of ensemble machine learning techniques, combining several models to improve the accuracy and reliability of decisions made from dynamic data.
The study specifically examined XGBoost, LightGBM, CatBoost and Random Forest, with the researchers combining the predictions of the models to produce final decisions.
Usiagwu and his colleagues said the approach was designed to address some of the major problems associated with dynamic data, including data noise, imbalance, different data formats, high processing speed and scalability.
The researchers also incorporated real-time data processing techniques, feature engineering, noise filtering and Synthetic Minority Oversampling Technique to improve the quality and balance of the data used by the models.
They further applied hyperparameter tuning, grid search and cross-validation to optimise the models and reduce the risk of overfitting.
The study found that the ensemble framework could process large-scale dynamic data streams with high accuracy and low latency, suggesting its potential for applications where decisions have to be made quickly.
The researchers noted that such applications could include healthcare monitoring, financial systems and autonomous technologies, where delays or inaccurate decisions could have significant consequences.
“The findings underscore the transformative potential of these models in domains like healthcare, finance, and autonomous systems, where real-time decisions are critical,” the researchers stated.
Beyond the study, Usiagwu has built a professional career around data analysis, digital marketing and business intelligence, with experience spanning healthcare, charity, banking and marketing.
He currently works as a Data Selection and Insight Officer at one of the leading charity organizations in United Kingdom, where he analyses supporter behaviour, feedback and campaign performance to improve supporter journeys and assist decision-making.
His previous roles include Business Intelligence Analyst with National Health Service Professionals and Marketing Research Analyst Team Lead at Detutu Media Digital Marketing Agency.
His professional experience includes the use of Power BI, advanced Excel, SQL, data modelling, data visualisation and R programming, while his academic background includes a master’s degree in Digital Marketing from Salford University and a bachelor’s degree in Accounting from the National Open University of Nigeria.
Usiagwu’s research adds to his professional focus on using data and technology to identify patterns, improve decision-making and develop practical solutions to challenges created by increasingly complex and fast-moving digital environments.
TAGS:
📢 ADVERTISEMENT DISCLAIMER: Links above are sponsored posts. The Nation assumes no liability or responsibility for the claims, products, or services offered by third-party advertisers. Proceed with discretion.
Stay informed and ahead of the curve! Follow The Nation Newspaper on WhatsApp for real-time updates, breaking news, and exclusive content. Don’t miss a headline — join now!
Get instant breaking news and exclusive updates right on your feed! Subscribe to The Nation Newspaper Telegram channel and never miss a headline.
PAN lauds Oluyede, troops for improved security nationwide, calls for stronger citizen support46 minutes ago
‘Leaving wealth for children not my belief’, says Spyro1 hour ago
Minister bags 2026 Goalkeepers Champions by Gates Foundation 1 hour ago
FAAC revenue deducted monthly to service Peter Obi’s loans – Anambra Commissioner1 hour ago
