DATA-DRIVEN STRATEGIES FOR EARLY DETECTION OF FINANCIAL FRAUD IN MOBILE MONEY SYSTEMS: A CASE STUDY OF NIGERIA'S MOBILE MONEY ECOSYSTEM

JOSEPH JEREMIAH ADEKUNLE; LINUS ONUORAH; MICHAEL BINUYO; THEOPHILUS LARTEY

doi:10.70382/sjasor.v10i9.038

Authors

JOSEPH JEREMIAH ADEKUNLE Department of Computer Science, National Open University of Nigeria. Author
LINUS ONUORAH Department of Mechanical Engineering, University of Nigeria, Nsukka, Enugu State, Nigeria Author
MICHAEL BINUYO Department of Computer Science, University of Hertfordshire, Hatfield, United Kingdom. Author
THEOPHILUS LARTEY Department of Statistics, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana Author

DOI:

https://doi.org/10.70382/sjasor.v10i9.038

Keywords:

Mobile money, financial fraud, fraud detection, Nigeria, Sub-Saharan Africa, fintech, machine learning

Abstract

The rapid expansion of mobile money services in Sub-Saharan Africa (SSA) has revolutionized financial inclusion, but it has also created new vulnerabilities for financial fraud. This study examines data-driven strategies for early detection of financial fraud in mobile money systems, with a specific focus on Nigeria's mobile money ecosystem, including MTN MoMo, Airtel Money, PalmPay, and OPay. Through a comprehensive analysis of current fraud detection methodologies, machine learning approaches, and regulatory frameworks, this research identifies key strategies for enhancing fraud prevention in mobile financial services. The findings reveal that integrated approaches combining behavioral analytics, transaction pattern recognition, and real-time monitoring systems are most effective in combating mobile money fraud. The study recommends the adoption of collaborative fraud detection frameworks among mobile money operators and strengthened regulatory oversight to protect Nigeria's growing mobile money user base.