Agentic AI Orchestrated Conversational Payment Pipelines with Drift-Aware Transaction
DOI:
https://doi.org/10.15662/IJEETR.2024.0603008Keywords:
Agentic Artificial Intelligence, Conversational Payment Systems, Multi-Agent Orchestration, Concept Drift Detection, Adaptive Fraud Detection, Transaction Risk Validation, Conversational FinTech, Intelligent Payment Pipelines, Behavioral Anomaly Detection, AI-Driven Financial SecurityAbstract
Chatbots and voice assistant applications are becoming a part of digital finance as a conversational payment system, but current systems are based on fixed piping and rule-based fraud detectors that fail to keep up with changing behavioral patterns in transactions and concept drift. The present paper suggests an Agentic AI-coordinated conversational payment pipeline with drift-aware transaction validation that is meant to enhance security, flexibility, and automation in financial transactions. The recommended structure uses a multi-agent approach, which includes conversational interface agent, orchestration agent, payment execution agent, and drift-sensitive validation engine. The validation module is based on adaptive machine learning model and behavioral drift technology capable of dynamically measuring transaction risk using user and contextual pattern changes. The framework effectively eliminates the shortcomings of the static validation framework by allowing free coordination of agents and ongoing detection of fraud through transaction streams, with low latency. Experimental analysis on synthetic datasets of payments proves to be better in detection and resistant to behavioral drift than standard rule-based and single-model techniques
References
1. Albrecht, T., Baier, M.-S., Gimpel, H., Meierhöfer, S., Röglinger, M., Schlüchtermann, J., & Will, L. (2023), Leveraging Digital Technologies in Logistics 4.0: Insights on Affordances from Intralogistics Processes. Information Systems Frontiers. https://doi.org/10.1007/s10796-023-10394-6.
2. Panneer Selvam Viswanathan.Agentic ai: A comprehensive framework for autonomous decision making systems in artificial intelligence.International Journal of Computer Engineering and Technology, 16(1):862–880, 2025.IJCET, ISSN Print: 0976 6367; Online: 0976 6375.
3. B. Archibald, M. Calder, M. Sevegnani, and M. Xu.Quantitative modelling and analysis of bdi agents.Softw. Syst. Model., 23(2):343–367, 2024.
4. L. E. Erdogan et al.Plan-and-act: Improving planning of agents for long-horizon tasks.arXiv [cs.CL], 2025.
5. Constructions Aeronautiques, Adele Howe, Craig Knoblock, ISI Drew McDermott, Ashwin Ram, Manuela Veloso, Daniel Weld, David Wilkins Sri, Anthony Barrett, Dave Christianson, et al. PDDL – the planning domain definition language. Technical Report, Tech. Rep., 1998.
6. Aaron Baird and Likoebe Maruping. The Next Generation of Research on IS Use: A Theoretical Framework of Delegation to and from Agentic IS Artifacts. Management Information Systems Quarterly, 45(1):315–341, March 2021. ISSN ISSN 0276-7783/ISSN 2162-9730. URL https://aisel.aisnet.org/misq/vol45/iss1/12.
7. Pengyu Zhao, Zijian Jin, and Ning Cheng.An in-depth survey of large language model-based artificial intelligence agents.2023.
8. Shuaihang Chen, Yuanxing Liu, Wei Han, Weinan Zhang, and Ting Liu.A survey on LLM-based multi-agent system: Recent advances and new frontiers in application.2024.
9. R. N. Thomas and R. Gupta.A survey on machine learning approaches and its techniques.In 2020 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), pages 1–6, 2020.
10. T. Nithya, V. Nivas Kumar, Gayathri, S. Deepa, V. C, and R. Siva Subramanian.A comprehensive survey of machine learning: Advancements, applications, and challenges.In 2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), pages 354–361, 2023.
11. William G. Hatcher and Wei Yu.A survey of deep learning: Platforms, applications and emerging research trends.IEEE Access, 6:24411–24432, 2018.
12. Shengli Dong, Peilin Wang, and Ke Chen Abbas.A survey on deep learning and its applications.Computer Science Review, 40:100379, 2021.
13. Talaei Khoei, H. Ould Slimane, and N. Kaabouch.Deep learning: Systematic review, models, challenges, and research directions.Neural Computing and Applications, 2023.
14. Pooja Chhabra and D. S. Goyal.A thorough review on deep learning neural network.In 2023 International Conference on Artificial Intelligence and Smart Communication (AISC), pages 220–226, 2023.
