Electronic Thesis/Dissertation
 

Scam Call Detection and Categorization: A Machine Learning Approach to Thwart Telecommunications Fraud

Open Access Deposited

Phone scam calls have become a feature of a user’s daily life. A user can almost expect to receive at least one scam call a day. Threat actors use these calls as a medium or an attack vector to execute further cybercrimes such as identity theft and financial fraud. This issue has impacted and continues to impact society 20 years later by continuously evolving and evading various state-of-the-art methods and techniques. In an effort to address this problem, this praxis introduces a machine learning model for both binary prediction and multi-class classification of scam calls. The model presented is developed by using data aggregated from the United States Federal Trade Commission (FTC) organization, phone number metadata, and the Universal Licensing System. This data provides insight into known scam calls between the months of October 2023 and December 2023. The solution provided in this praxis not only detects incoming phone calls as malicious or authentic but can further categorize those calls into six unique classes: Authentic, Medical, Utilities, Impersonator, Technical, and Financial. These categories or labels aim to provide a user with more insight into the intention of a caller, especially in circumstances where the area code of an incoming call is familiar, to prevent a suspected malicious call from being answered. The objective of the solution presented is to reduce the likelihood that a user becomes a victim to cybercrime conducted over the phone.

Author Language Date created Type of Work License
  • All rights reserved
Rights statement GW Unit Degree Advisor Committee Member(s) Persistent URL

Notice to Authors

If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.

Thumbnail Title Date Uploaded Visibility Actions
Preview of Pierre_gwu_0075A_17036.pdf File 2025-04-11 Embargo