Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68412
Volume:
10 |
10 |
Oct 2026
Pages:
1-2
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Artificial Intelligence and Machine Learning
Sri Shakthi Institue of Engineering and Technology
Department of Artificial Intelligence and Machine Learning
Sri Shakthi Institue of Engineering and Technology
Department of Artificial Intelligence and Machine Learning
Sri Shakthi Institue of Engineering and Technology
Department of Artificial Intelligence and Machine Learning
Sri Shakthi Institue of Engineering and Technology
Department of Artificial Intelligence and Machine Learning
Sri Shakthi Institue of Engineering and Technology
Real time payment fraud scoring angd agentic anti money laundering investigation platform is a proposed financial-crime analytics platform combining real-time payment fraud scoring with an agent-assisted anti-money-laundering (AML) investigation workflow. Its fraud-scoring path is designed to use machine-learning models, engineered transaction features, online feature retrieval, and explainability outputs to identify potentially suspicious payments. An entity-graph layer is intended to reveal relationships among accounts, devices, IP addresses, and transactions that may indicate coordinated activity. A multi-agent AML workflow is designed to support link analysis, transaction-pattern review, adverse-media retrieval, investigation narrative drafting, and quality checks. Human review remains central to consequential decisions and suspicious activity report submission. This paper summarises the system concept, architecture, methodology, reported implementation progress, evaluation approach, limitations, and planned next steps. No numerical performance results are claimed because verified experimental metrics were not provided.
KEYWORDS
AegisFlow proposes an integrated approach to payment fraud scoring and AML investigation by combining machine learning, online/offline feature processing, graph analytics, explainability, and agent-assisted case workflows. The implementation work reported so far establishes foundational feature, graph, modelling, and evaluation components. Further integration, security review, end-to-end testing, and evidence-based performance reporting are necessary before the platform can be described as production-ready.
1. Chen, T. and Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/2939672.2939785 2. Lundberg, S. M. and Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems (NeurIPS). https://arxiv.org/abs/1705.07874 3. IEEE-CIS Fraud Detection dataset, Kaggle. https://www.kaggle.com/competitions/ieee-fraud-detection (dataset reference; use only if this dataset is actually used in the project). 4. LangGraph documentation. https://langchain-ai.github.io/langgraph/ (technical resource for the proposed agent workflow). 5. MLflow documentation. https://mlflow.org/docs/latest/index.html 6. FastAPI documentation. https://fastapi.tiangolo.com/
Publication Date
11/13/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
1
Total views since publication
PDF Downloads
0
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...