FRAUD DETECTION IN NIGERIAN INVESTMENT ADVISORY SECTOR USING MACHINE LEARNING ALGORITHMS
Keywords:
Fraud detection, Nigerian investment, Random Forest, Machine learning, Class imbalanceAbstract
The increasing rate of financial fraud within Nigeria’s investment advisory sector presents a pressing challenge, particularly as traditional detection methods struggle to keep pace with evolving fraudulent behaviors. With the growing reliance on technology in the financial ecosystem, machine learning offers a promising solution for detecting anomalies and minimizing risk. This study explores the application of three machine learning algorithms: Logistic Regression, Random Forest, and XGBoost to predict fraudulent transactions in the Nigerian investment advisory landscape. To address class imbalance which is a common issue in fraud datasets, hybrid resampling using SMOTE and Tomek Links was implemented. The Random Forest model emerged as the most robust, maintaining consistent performance across key metrics even after resampling. This research also emphasizes the importance of integrating cost-sensitive learning, regular model retraining, and cross-validation to adapt to Nigeria’s dynamic fraud landscape. The study presents a scalable approach to enhancing fraud detection systems and safeguarding investor trust in the sector.

Published
How to Cite
Issue
Section
Copyright (c) 2025 Johnson O. Fatokun, Mustapha Sikiru, Funmilola Balogun, Daberechi D. Okorie

This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
Most read articles by the same author(s)
- Chinedu Peter, Funmilola Balogun, Omotosho Adewumi Adeyemi, AN EXPLORATION OF ANTIMULTIGROUP EXTENSIONS , FUDMA JOURNAL OF SCIENCES: Vol. 8 No. 5 (2024): FUDMA Journal of Sciences - Vol. 8 No. 5
- Jessica Mrumun Gyegwe, Funmilola Balogun, Leke Oni, M. S. Omeiza, MOTIONS AROUND THE OUT-OF-PLANE EQUILIBRIUM POINTS FOR BINARY LALANDE 21258, BD+195116, ROSS 614, 70 OPHIUCHI AND 61 CYGNI SYSTEMS , FUDMA JOURNAL OF SCIENCES: Vol. 9 No. 2 (2025): FUDMA Journal of Sciences - Vol. 9 No. 2