Detecting Advance Fee Fraud Using NLP Bag of Word Model

Abstract

Advance Fee Fraud (AFF) is a form of Internet fraud prevalent within the Cybercrimes domain in literature. Evidence shows that huge financial assets are stolen from the global economy as a result of AFF. Consequently, this paper presents a fraudulent email classifier (FEC) that detects and classifies an email as fraudulent or non-fraudulent using Natural Language Process (NLP) model referred to as Bag-of-Words (BoW). The classifier is designed and trained to detect and classify AFF that originate from known sources using Nigeria as a Case study. Dataset is obtained and used for the training while testing the classifier logs. Experimentally, the classifier was trained using various machine learning algorithms with BoW generated as predictors. By selecting the best algorithms, the classifier was tested and found to perform satisfactorily.