Review Article
A Multi-layer Perceptron Framework for Pre-admission Disciplinary Risk Prediction in Nigerian Universities:
A Fairness-aware Approach Using Synthetic Data
Issue:
Volume 10, Issue 1, June 2026
Pages:
1-13
Received:
20 April 2026
Accepted:
29 April 2026
Published:
18 May 2026
Abstract: Nigerian universities have long struggled to identify, before matriculation, which applicants are likely to become disciplinary problems on campus. Existing screening procedures are largely manual and reactive — problems surface after enrolment rather than at the gate. To close this gap, we built and tested a Multi-Layer Perceptron classifier that assigns each applicant a probabilistic risk score at the point of admission, giving institutional officers an evidence-based basis for early counselling and targeted resource deployment, well before misconduct occurs. Working with real student records was not feasible. Nigeria's data protection obligations impose strict constraints on profiling, and authentic admission data from universities was unavailable for this research. We therefore generated 5,000 synthetic applicant profiles using a Conditional Tabular GAN, a method purpose-built for datasets that mix continuous, ordinal, and categorical variables. Three statistical tests — the Kolmogorov–Smirnov statistic, Wasserstein distance, and Jensen–Shannon divergence — confirmed that the synthetic profiles reproduced the structural properties of realistic admission populations with high fidelity. Under five-fold stratified cross-validation, the MLP returned an accuracy of 0.841 ± 0.018, F1-score of 0.812 ± 0.021, and AUC-ROC of 0.891 ± 0.014, outperforming Logistic Regression, Random Forest, SVM, and XGBoost across all reported metrics. Two findings deserve particular attention. First, SHAP attribution analysis singled out prior disciplinary record and JAMB score as the variables driving predictions most strongly — a result with direct implications for what admissions officers should scrutinize. Second, the model treated applicants from different geopolitical zones unequally; an EOD of 0.078 across zones exceeded acceptable thresholds. Fairness-regularized retraining brought that Figure down to 0.043 with less than one percentage point of accuracy lost. To prevent the system from operating as a black box, a three-tier human-in-the-loop review protocol is proposed, and the entire deployment framework is mapped against Nigeria's National Data Protection Regulation and Data Protection Impact Assessment requirements.
Abstract: Nigerian universities have long struggled to identify, before matriculation, which applicants are likely to become disciplinary problems on campus. Existing screening procedures are largely manual and reactive — problems surface after enrolment rather than at the gate. To close this gap, we built and tested a Multi-Layer Perceptron classifier that ...
Show More
Research Article
Development of Super-Fast Decision Support System for Optimum Packaging Material Selection
Issue:
Volume 10, Issue 1, June 2026
Pages:
14-26
Received:
30 April 2026
Accepted:
13 May 2026
Published:
28 July 2026
DOI:
10.11648/j.ijem.20261001.12
Downloads:
Views:
Abstract: This study developed a rapid Decision Support System (DSS) to improve the efficiency, reliability, accuracy, and consistency of packaging material selection through the automation of the Analytic Hierarchy Process (AHP). Traditional AHP-based selection methods are often time-consuming and computationally demanding, particularly when several criteria and alternatives must be evaluated. To address this limitation, this study adopted a systematic methodology in which the AHP technique was integrated into a Python-based application with a graphical user interface (GUI). Expert judgments were collected through pairwise comparisons and processed within the system to generate automated weight calculations, consistency evaluations, global rankings of alternatives, and sensitivity analysis. The results showed that plastic had the highest global priority score of 0.4202, making it the most preferred packaging material in the decision framework. This was followed by paperboard (0.2315), glass (0.2003), and metal (0.1481). The sensitivity analysis further showed that the ranking remained stable under small changes of 0 to 20% in expert judgments, indicating that the outcomes were reliable and robust. The developed DSS reduced decision-making time by an average of 21.29% compared with a conventional AHP tool. In addition, the system provides automated computations, downloadable graphical outputs, and real-time sensitivity analysis, making it a practical, efficient, and user-friendly tool for selecting packaging materials.
Abstract: This study developed a rapid Decision Support System (DSS) to improve the efficiency, reliability, accuracy, and consistency of packaging material selection through the automation of the Analytic Hierarchy Process (AHP). Traditional AHP-based selection methods are often time-consuming and computationally demanding, particularly when several criteri...
Show More
,
Solomon Olalekan Akinola
