LEVERAGING ARTIFICIAL INTELLIGENCE TO DETECT AND PREVENT FRAUD IN DIGITAL PAYMENTS
Abstract
Digital payments are big business right now, and what is the new money technology we can do business all over the globe to a level which is astronomical. The company has more vulnerabilities and it is now easier to commit fraud, both online and off. It is happening as electronic payments are growing in popularity because they are more convenient, and may help people with poor credit obtain utilities. The Great American Smokeout Fighting Fraud on the Internet The Scammers Who Steal Hearts and Money There were about 250 men behind a blue-plate glass window in an Appalachian shop who had paid for a shot at pulling up gold, only to learn they would have some weeks of trouble. And this is where the AI has taken safe online payments to another level. Digital payments should be more secure: With AI to catch fraud, we can analyze gigantic amounts of real-time transactional data and halt suspicious activity in its tracks with disruptive methods that prevent the issue before it arises. It even shows how A.I. could be used to stop fraud in the future and what companies and regulators can do to ensure that A.I. comes into the world properly, and shields online payments as it does so. For example, AI-powered platforms and solutions have been driving development of a more secure and predictable online transactions and promoting trust in a global digital economy.
References
Agwu, E. (2024). Financial fraud detection using Value-at-Risk with machine learning in skewed data.
Aldosari (2024) — GRFO + KNN (with SMOTE) ≈ 99.98% and outperforming DCNN/CatBoost
Al-Quayed, M., et al. (2024). Utilizing blockchain and smart contracts for enhanced fraud prevention (survey/preprint). arXiv:2407.17765. (Discusses blockchain + ML for insurance fraud prevention; contextually related).
Al-Quayed, M., et al. (2024). Utilizing blockchain and smart contracts for enhanced fraud prevention. arXiv:2407.17765.
Bhowte et al. (2024) — exhaustive survey of ML in financial-service fraud https://ieeexplore.ieee.org/author/614775320328834
Etukudo, U., & Agwu, E. (2024). Financial fraud detection using Value-at-Risk with machine learning in skewed data. International Journal of Research in Engineering, Science and Technology (IJRDST). (Preprint/Index pages available).
Ghatee, M. (2025). A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions. Expert Systems with Applications, 262, 125661. (Early 2025 issue; aligns with resampling + GBM sequence modeling claims).
Ghatee, M. (2025). A distribution-preserving method for resampling combined with LightGBM-LSTM for sequence-wise fraud detection in credit card transactions. Expert Systems with Applications, 262, 125661.
Gudivaka et al. (2024) — “VAEGAN-” + CNN and novel oversampling, accuracy ≈ 99.78%
Huang, T., Wang, X., Ma, Y., & Dr.Naveen Prasadula (2024). A deep learning method of credit card fraud detection based on Continuous-Coupled Neural Network (CCNN). Mathematics, 13(5), 819. (Recent deep-learning approach for card fraud).
Huang, T., Wang, X., Ma, Y., & Chen, Z. (2024). A deep learning method of credit card fraud detection based on continuous-coupled neural network. Mathematics, 13(5), 819.
https://orcid.org/my-orcid?orcid=0000-0002-9764-6048
https://scholar.google.com/citations?user=99wmG2IAAAAJ&hl=en
J. N. V. R. Swarup Kumar, R., & Ravikanth, D. (2023/2024). Digital verification: An efficient fraud document detection for insurance claims using IoT and ML approaches (preprint). (IoT + ML for insurance claims; related to the “IoT-specific insurance fraud” topic).
Kalaiselvi et al. (2024) — ensemble ML for suspicious email (phishing/spoofing)
Kour (2024) — ML in finance (fraud, risk, customer service)
Mostafa et al. (2024) — RF vs. GB, NB, LR on credit-card fraud with RF best
Patel et al. (2024) — SMOTE-Tomek + hyperparameter tuning; XGBoost ≈ 99.95% on mobile financial fraud
Pendalwar et al. (2024) — RF, SVM, NB, KNN, XGBoost, LightGBM; PCA and GANs for balancing
Singh, A., & co-authors (2025). UPI fraud detection using machine learning. In Proceedings of Smart Innovation, Systems and Technologies (Springer chapter, first online 2025; aligns with UPI ML approaches).
Sharan et al. (2024) — IoT-specific insurance claim fraud detection with real-time sensors, anomaly/clustering/bracketing
Singh, A., & co-authors (2025). UPI fraud detection using machine learning. In Smart Innovation, Systems and Technologies. Springer.
Taskiran, A., & co-authors (2024). Blockchain-assisted healthcare insurance fraud detection framework using ensemble learning. Computers & Electrical Engineering. (Blockchain + ML for medical claim fraud).
Taskiran, A., et al. (2024). Blockchain-assisted healthcare insurance fraud detection framework using ensemble learning. Computers & Electrical Engineering.
Tawil, A. A., et al. (2024). Comparative analysis of ML algorithms for email phishing detection using TF-IDF, Word2Vec, and BERT. Computers, Materials & Continua.
Tawil, A. A., et al. (2024). Comparative analysis of ML algorithms for email phishing detection using TF-IDF, Word2Vec, and BERT. Computers, Materials & Continua. (Broad email-fraud/phishing ML comparison).
Vii et al. (2024) — BiGRU + Capsule Network for e-commerce fraud ≈ 95.44%
Wu, B., Qi, X., & Chen, Y. (2024). Encoder–decoder graph neural network for credit card fraud detection. Journal of King Saud University – Computer and Information Sciences. (GNN approach for card fraud).
Wu, B., Qi, X., & Chen, Y. (2024). Encoder–decoder graph neural network for credit card fraud detection. Journal of King Saud University – Computer and Information Sciences.
