# Enhancing Customer Contact Efficiency with Graph Neural Networks in Credit Card Fraud Detection Workflow

arXiv: https://arxiv.org/abs/2504.02275 · HTML: https://mlsanity.com/paper/2504.02275/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 17 references that are in the map.
- First posted on arXiv 3 Apr 2025.

## Builds on (most cited first, 13 of 13)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [RATT: A Thought Structure for Coherent and Correct LLM Reasoning](https://mlsanity.com/paper/2406.02746/) (2024)
- [Analysis of KNN Density Estimation](https://mlsanity.com/paper/2010.00438/) (2020)
- [RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions](https://mlsanity.com/paper/2501.00353/) (2024)
- [BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra](https://mlsanity.com/paper/2402.17882/) (2024)
- [NEVLP: Noise-Robust Framework for Efficient Vision-Language Pre-training](https://mlsanity.com/paper/2409.09582/) (2024)
- [CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference](https://mlsanity.com/paper/2501.15852/) (2025)
- [Minimax Optimal Q Learning with Nearest Neighbors](https://mlsanity.com/paper/2308.01490/) (2023)
- [Deep Semantic Graph Learning via LLM based Node Enhancement](https://mlsanity.com/paper/2502.07982/) (2025)
- [CPDR: Towards Highly-Efficient Salient Object Detection via Crossed Post-decoder Refinement](https://mlsanity.com/paper/2501.06441/) (2025)
- [DDUNet: Dual Dynamic U-Net for Highly-Efficient Cloud Segmentation](https://mlsanity.com/paper/2501.15385/) (2025)
- [Credit Card Fraud Detection Using Enhanced Random Forest Classifier for Imbalanced Data](https://mlsanity.com/paper/2303.06514/) (2023)
- [Fraud/Uncollectible Debt Detection Using a Bayesian Network Based Learning System: A Rare Binary Outcome with Mixed Data Structures](https://mlsanity.com/paper/1302.4945/) (2013)

## Built on by (most cited first, 8 of 8)

- [QFFT, Question-Free Fine-Tuning for Adaptive Reasoning](https://mlsanity.com/paper/2506.12860/) (2025)
- [Resilient Routing: Risk-Aware Dynamic Routing in Smart Logistics via Spatiotemporal Graph Learning](https://mlsanity.com/paper/2601.13632/) (2026)
- [Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback](https://mlsanity.com/paper/2505.15572/) (2025)
- [A Narrative Review on Large AI Models in Lung Cancer Screening, Diagnosis, and Treatment Planning](https://mlsanity.com/paper/2506.07236/) (2025)
- [Distribution Shift Aware Neural Tabular Learning](https://mlsanity.com/paper/2508.19486/) (2025)
- [Non-Intrusive Graph-Based Bot Detection for E-Commerce Using Inductive Graph Neural Networks](https://mlsanity.com/paper/2601.22579/) (2026)
- [Segregation and Context Aggregation Network for Real-time Cloud Segmentation](https://mlsanity.com/paper/2504.14178/) (2025)
- [Predicting Mortgage Default with Machine Learning: AutoML, Class Imbalance, and Leakage Control](https://mlsanity.com/paper/2602.00120/) (2026)

## Abstract (arXiv)

Credit card fraud has been a persistent issue since the last century, causing significant financial losses to the industry. The most effective way to prevent fraud is by contacting customers to verify suspicious transactions. However, while these systems are designed to detect fraudulent activity, they often mistakenly flag legitimate transactions, leading to unnecessary declines that disrupt the user experience and erode customer trust. Frequent false positives can frustrate customers, resulting in dissatisfaction, increased complaints, and a diminished sense of security. To address these limitations, we propose a fraud detection framework incorporating Relational Graph Convolutional Networks (RGCN) to enhance the accuracy and efficiency of identifying fraudulent transactions. By leveraging the relational structure of transaction data, our model reduces the need for direct customer confirmation while maintaining high detection performance. Our experiments are conducted using the IBM credit card transaction dataset to evaluate the effectiveness of this approach.