Application of Machine Learning Classification to Detect Fraudulent E‑wallet Deposit Notification SMSes
Date
2020-06-30
Authors
Enkono, Fillemon S.
Suresh, Nalina
Journal Title
Journal ISSN
Volume Title
Publisher
LINK Centre, University of the Witwatersrand (Wits), Johannesburg
Abstract
Fraudulent e-wallet deposit notification SMSes designed to steal money and goods from m-banking users have become pervasive in Namibia. Motivated by an observed lack of mobile applications to protect users from such deceptions, this study evaluated the ability of machine learning to detect the fraudulent e-wallet deposit notification SMSes. The naïve Bayes (NB) and support vector machine (SVM) classifiers were trained to classify both ham (desired) SMSes and scam (fraudulent) e-wallet deposit notification SMSes. The performances of the two classifier models were then evaluated. The results revealed that the SVM classifier model could detect the fraudulent SMSes more efficiently than the NB classifier.
Description
Keywords
m-banking, e-wallets, short message service messages (SMSes), deposit notification, fraud, ham SMSes, scam SMSes, detection, machine learning, classifiers, naïve Bayes (NB), support vector machine (SVM), classification accuracy (CA), feature extraction, feature selection
Citation
Enkono, F. S., & Suresh, N. (2020). Application of machine learning classification to detect fraudulent e‑wallet deposit notification SMSes. The African Journal of Information and Communication (AJIC), 25, 1-13. https://doi.org/10.23962/10539/29195