Application of Artificial Intelligence to Curb Fraud Among the Elderly
DOI:
https://doi.org/10.61173/z998wb83Keywords:
Artificial Intelligence, Elderly Fraud Preven-tion, Machine Learning, Natural Language Processing, Financial SecurityAbstract
The new technologies are being developed due to the rapid AI growth, which is ready to use in the fight against financial fraud, especially for such vulnerable communities as the elderly. This paper focuses on how AI technologies can be implemented in various areas of fraud protection surpassing from machine learning algorithms and natural language processing up to facial recognition. The paper sets out an analysis of existing AI-based fraud prevention methods, highlighting their advantages and disadvantages, and advices on improving their functional efficiency. The application of publicly available datasets for fraud detection shows that AI can get high accuracy in dealing with suspicious activities. And though it exists, its concerns of privacy data, personal bias, and the necessary adaptation of the system for the use of seniors with poor digital skills. The paper ends with a number of approaches for the development of ethical, transparent, and user-friendly AI systems which will enable older people to make deliberate decisions concerning the prevention of scams.
References
[1] AARP, “The $90 Billion Scam: Elder Financial Abuse,” AARP, 2023.
[2] S. Anderson, “Elderly Vulnerabilities in the Digital Age,” Journal of Gerontechnology, vol. 19, no. 2, pp. 45–54, 2022.
[3] FBI IC3, “Elder Fraud Report 2022,” Federal Bureau of Investigation, 2023.
[4] X. Li, Y. Zhang, “Machine Learning for Banking Fraud Detection,” IEEE Access, vol. 9, pp. 12545–12558, 2021.
[5] R. Kumar, “AI-based Monitoring for Social Media Scams,” ACM Transactions on Internet Technology, vol. 22, no. 4, 2022.
[6] K. Brown, “Detecting Manipulative Language in Fraud Communications,” Natural Language Engineering, vol. 28, no. 3, pp. 377–394, 2022.
[7] J. Smith, “Random Forests in Financial Fraud Detection,” Expert Systems with Applications, vol. 178, 2021.
[8] T. Lee, “Phishing Detection using BERT,” Proc. of ACL, 2021.
[9] M. Patel, “Facial and Voice Biometrics in Identity Protection,” IEEE Security & Privacy, vol. 20, no. 1, 2022.
[10] L. Carter, “Human-in-the-Loop AI for Trust Building,” AI & Society, 2021.
[11] IEEE-CIS, “Fraud Detection Dataset,” IEEE Computational Intelligence Society, 2020.
[12] Hugging Face, “Transformers: State-of-the-art NLP,” 2023.
[13] Z. Wang, “AI vs Rule-based Systems in Fraud Detection,” Information Systems Frontiers, vol. 24, 2022.
[14] GDPR, “General Data Protection Regulation,” EU, 2018.
[15] M. Johnson, “Bias and Fairness in AI,” Ethics in AI Journal, vol. 3, 2021.
[16] D. Nguyen, “Improving Digital Literacy for Seniors,” Educational Gerontology, vol. 48, 2022.
[17] P. Zhao, “Real-Time Fraud Detection Systems,” IEEE Transactions on Big Data, vol. 8, no. 5, 2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
