Mr. Rohit Tewari

Credit Card Fraud Detection based on Time-Aware Multi-Relational Guided Graph Neural Network (TMR-GGNN)

Abstract:

In recent years, credit card fraud detection has faced significant challenges due to highly imbalanced data, evolving fraud patterns, and complex relational structures among transaction entities. To address these issues, this research proposes a novel framework called Time-aware Multi-Relational Guided Graph Neural Network (TMR-GGNN). Particularly, the proposed TMR-GGNN extends the encoder–decoder Graph Neural Network GNN architecture by modeling heterogeneous interactions across customers, merchants, devices, and IPs over temporal windows. Subsequently, the proposed TMR-GGNN approach constructs a dynamic, multi-relational graph and incorporates a time-aware relational attention mechanism within the encoder to adaptively weigh the transaction relevance based on temporal proximity and semantic context. Consequently, the decoder employs a contrastive learning module to distinguish between real and synthesized transaction patterns, while improving the model’s generalization of rare fraud cases. Additionally, to effectively manage severe class imbalances and emphasize discriminative learning, a composite loss function combining Information Noise-Contrastive Estimation (InfoNCE)-based contrastive loss with Focal Loss is introduced. This integration assists in improving fraud identification while mitigating false negatives.

Profile:

I am an IEEE Senior Member and ACM Member, certified through the Elsevier Researcher Academy Peer Reviewer Course, with nearly two decades of experience leading large-scale technology modernization initiatives across government, finance, and public administration.
With over 19 years of experience in enterprise application development, cloud architecture, and data modernization, I specialize in building scalable, secure, and intelligent systems that drive digital transformation across industries. My career spans banking, finance, healthcare, and telecom, where I’ve led mission-critical modernization programs blending innovation with measurable performance gains.
As a Cloud and AI Innovation Leader, I have extensive expertise designing cloud-native architectures on AWS, integrating AI/ML pipelines for predictive analytics, risk management, and anomaly detection. I provide data-to-decision capabilities using modern engineering and automation principles.
I have also directed Salesforce and legacy system modernization, overseeing complex migrations from on-prem environments to cloud CRMs, ensuring data integrity, scalability, and compliance.