AI-Powered Fraud Detection Mechanisms in Salesforce Financial CRM Systems Using Cloud Infrastructure
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V7I1P129Keywords:
Artificial Intelligence, Fraud Detection, Salesforce CRM, Cloud Computing, Machine Learning, Financial Security, Anomaly Detection, Big Data AnalyticsAbstract
The high rate of digitization of financial services has further compounded customer relationships and interaction with customers in Customer Relationship Management (CRM) systems. The salesforce financial CRM systems have become supreme applications in customer data, services and financial interactions. Nevertheless, increased digital transactions have equally heightened the risk associated with financial fraud which include identity theft, manipulations of transactions, account hijackings and insider threats. Conventional rule-based fraud detection systems are becoming less sufficient to respond to high-level and adaptive as well as massive fraud trends. The study proposes an overall design of AI-based fraud detection systems as embedded in Salesforce Financial CRM interfaces through cloud environments. The solution that will be discussed follows the application of machine learning, deep learning, and real-time analytics that are open on scalable cloud deployments, positively affecting the detection of fraud, decrease in false positives, and the ability to comply with regulations. This paper discusses supervised, unsupervised and hybrid anomaly detects and risk scoring learning models with cloud-native high-availability and low-latency architectures. The article presents the design, implementation, and evaluation of end-to-end fraud detection pipeline, which includes features of data ingestion, data preprocessing, and feature engineering, model training, deployment, and continuous monitoring. The focus is made on security, privacy, and the standard compliance (GDPR, PCI-DSS, and SOC 2). Exposure to experimental evidence shows that the proposed system detects more accurately and faster by 18 and 25 percent than conventional systems, respectively. The results demonstrate the relevance of AI-based intelligence and scalability of cloud computing in contemporary financial type of CRM. The current work adds to a viable and scalable framework that can be adopted by financial entities interested in raising the level of resilience to frauds in Salesforce ecosystems.
References
[1] Dai, S. (2024). Banking Business in Digital Transformation: The Role of Cloud Computing. Journal of Progress in Engineering and Physical Science, 3(4), 76-83.
[2] Nutalapati, P. (2024). A Review on Cloud Computing in Finance-Transforming Financial Services in the Digital Age. International Research Journal of Engineering & Applied Sciences| Irjeas. org, 12(3), 35-45.
[3] George, M. Z. H., Alam, M. K., & Hasan, M. T. (2025). Machine learning for fraud detection in digital banking: a systematic literature review REVIEW. arXiv preprint arXiv:2510.05167.
[4] Yazici, Y. (2020). Approaches to Fraud detection on credit card transactions using artificial intelligence methods. arXiv preprint arXiv:2007.14622.
[5] Ileberi, E., Sun, Y., & Wang, Z. (2022). A machine learning based credit card fraud detection using the GA algorithm for feature selection. Journal of Big Data, 9(1), 24.
[6] Albalawi, T., & Dardouri, S. (2025). Enhancing credit card fraud detection using traditional and deep learning models with class imbalance mitigation. Frontiers in Artificial Intelligence, 8, 1643292.
[7] Xu, B., Wang, Y., Liao, X., & Wang, K. (2023). Efficient fraud detection using deep boosting decision trees. Decision Support Systems, 175, 114037.
[8] Chy, M. K. H. (2024). Proactive Fraud Defense: Machine Learning's Evolving Role in Protecting Against Online Fraud. arXiv preprint arXiv:2410.20281.
[9] Compagnino, A. A., Maruccia, Y., Cavuoti, S., Riccio, G., Tutone, A., Crupi, R., & Pagliaro, A. (2025). An introduction to machine learning methods for fraud detection. Applied Sciences, 15(21), 11787.
[10] Chen, Y., Zhao, C., Xu, Y., Nie, C., & Zhang, Y. (2025). Deep learning in financial fraud detection: Innovations, challenges, and applications. Data Science and Management.
[11] Zheng, P., Yuan, S., & Wu, X. (2019, July). Safe: A neural survival analysis model for fraud early detection. In Proceedings of the AAAI conference on artificial intelligence (Vol. 33, No. 01, pp. 1278-1285).
[12] Potluri, S. (2025). The Role of AI and Machine Learning in Enhancing Payment Fraud Detection and Prevention in Cloud-Native Payment Systems. Journal of Computer Science and Technology Studies, 7(10), 233-239.
[13] Seemanapalli, K. (2025). API-Level Fraud Detection in Financial Systems: Real-Time AI and Behavioral Analytics Integration. Journal Of Engineering And Computer Sciences, 4(12), 27-35.
[14] Khan, S. (2025). AI-driven fraud detection in banking: The convergence of predictive analytics and Salesforce CRM automation. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 6(2), 1-11.
[15] Büyükbıçakcı, E. (2025). Anomaly Detection in Salesforce’s Transactional Data Using Machine Learning Techniques. Journal of Advanced Applied Sciences, 4(1-2), 1-15.
[16] del Mar Roldán-García, M., García-Nieto, J., & Aldana-Montes, J. F. (2017). Enhancing semantic consistency in anti-fraud rule-based expert systems. Expert Systems with Applications, 90, 332-343.
[17] Bolton, R. J., & Hand, D. J. (2002). Statistical fraud detection: A review. Statistical science, 17(3), 235-255.
[18] Raghavan, P., & El Gayar, N. (2019, December). Fraud detection using machine learning and deep learning. In 2019 international conference on computational intelligence and knowledge economy (ICCIKE) (pp. 334-339). IEEE.
[19] Olushola, A., & Mart, J. (2024). Fraud detection using machine learning. ScienceOpen Preprints.
[20] Davis, J. J., & Clark, A. J. (2011). Data preprocessing for anomaly based network intrusion detection: A review. computers & security, 30(6-7), 353-375.
[21] Carcillo, F., Le Borgne, Y. A., Caelen, O., Kessaci, Y., Oblé, F., & Bontempi, G. (2021). Combining unsupervised and supervised learning in credit card fraud detection. Information sciences, 557, 317-331.
