University of Ibadan Journal of Science and Logics in ICT Research

Comparison of Analytical Hierarchy Process and Fuzzy Analytical Hierarchy Process Models for E- Banking Websites Quality Evaluation

S.A Adepoju, C.D Shaba, Y.B Lasotte, A Ekundayo — Tue, 16 Dec 2025 00:00:00 +0000

The process of evaluating the quality of e-banking websites has gained rapid attention in recent years with the adoption of multi-criteria decision-making (MCDM) approaches. The Analytical Hierarchy Process (AHP) and the fuzzy AHP models which are well suited to determine the outcomes of the e-banking website quality evaluation are explored in this study. In both cases, the decision-making activity is broken into criteria and sub criteria usually arranged as a pairwise comparison matrix layout. Though the latter is meant to be an advancement over the former, this paper compares the performances of the two MCDM approaches in evaluating e-banking websites of top-four Nigerian banks by profit margin. The data was collected from 33 out of 50 initially selected respondents using e-banking apps in Minna, Niger State through a non-random sampling technique. The outcome showed that the AHP and FAHP models are closely correlated based on the ranking of the weights of criteria and alternatives used in the study. Using the Wilcoxon Signed Rank Test, the Asymp Sig. (2-tailed) of criteria and sub-criteria is 0.500 for AHP and FAHP models indicating highly correlated decisions of the respondents. Also, the Wilcoxon Signed Rank Test (Asymp Sig. (2-tailed)) of alternatives is 1.000 for AHP and FAHP models indicating fairly correlated decisions on e-banking websites quality of alternatives (banks). However, the FAHP performances were superior to the AHP, which is consistent with some existing studies.

Comparative Analysis of Machine Learning Models for Fraud Detection in Imbalanced Credit Card Transaction Datasets

C. C. Enehikhare, V. Odumuyiwa — Tue, 16 Dec 2025 00:00:00 +0000

Fraud detection in imbalanced datasets presents a major challenge in financial domains, particularly in credit card fraud detection. This paper presents a comparative analysis of popular machine learning models—Logistic Regression, Decision Trees, Random Forest, and XGBoost applied to real and simulated fraud datasets. Various data preprocessing techniques, such as SMOTE, Random Sampling, were employed to address class imbalance. The results indicate that ensemble models, particularly Random Forest and XGBoost, outperformed traditional models, achieving near-perfect F1-scores (0.999) and accuracies (0.999) across both datasets. These findings provide insight into model effectiveness in fraud detection tasks and offer a foundation for developing robust, adaptive fraud detection systems

Approximation Algorithm for Travelling Salesman Problem

R. O Oladele, D. M. Mobolaji — Tue, 16 Dec 2025 00:00:00 +0000

Designing approximation algorithms often involves, among other things, relaxing the integrality constraint and obtaining a convex relaxation of the problem. The most well-known relaxation schemes are the Linear Programming (LP) relaxation and Semi-Definite Programing (SDP) relaxation. While LP relaxation has been widely used for solving TSP, SDP has been rarely employed. The primary goal of this paper therefore is to employ SDP and develop approximation algorithm for metric TSP. The SDP relaxation of the TSP is first obtained, and the approximation algorithm is thereafter developed. When compared to optimal results of some standard TSP instances, implementation result showed a relatively fair performance.

Development of a Hybrid Blockchain-Based File Sharing System in a Cloud Environment

A. F Osuolale , O. D Alimi , I. T Okeowo — Wed, 10 Dec 2025 00:00:00 +0000

Conventional file storage and sharing systems encounter issues with security vulnerabilities, transparency shortcomings, and ineffective distribution. This initiative introduces an innovative blockchain-based framework for secure file sharing, addressing these challenges through the utilization of blockchain, Interplanetary File System (IPFS), and Advanced Encryption System (AES) encryption. The system uses a blockchain network to record file metadata like ownership, timestamps, and access permissions, ensuring data transparency and integrity. AES encryption secures data confidentiality, while IPFS efficiently distributes file chunks across nodes, enhancing availability and reliability. This approach creates a secure, efficient, and transparent file sharing solution. Performance evaluations demonstrate that the developed model outperforms existing models in terms of response time and requests per second, highlighting its efficiency under load.