Machine Learning-Based Detection of Mobile Money Scan Messages in Ghana: A Comparative Evaluation of Naive Bayes, Support Vector Machine, and Randon Forest Classifiers

Ibrahim Salifu, Muhaisin Tiyumba Nantogmah|October 29, 2026arXiv

Key Takeaway

Classical machine learning classifiers can reliably detect mobile money fraud in SMS with high accuracy using simple text features, making them practical for deployment on resource-constrained devices in developing markets.

Summary

This paper develops a machine learning system to detect mobile money scam SMS messages in Ghana using Naive Bayes, SVM, and Random Forest classifiers.

safety applications evaluation

Key Terms

tf-idf stratified-cross-validation matthews-correlation-coefficient auc-roc