What question did this study set out to answer?

Develop an automated end-to-end neural network architecture that models spatial and temporal transaction behaviors to detect credit card fraud without reliance on manual feature engineering.

April 3, 2020Open Access

Spatio-Temporal Attention-Based Neural Network for Credit Card Fraud Detection

View Full Paper

Ask AI

Bookmark

Develop an automated end-to-end neural network architecture that models spatial and temporal transaction behaviors to detect credit card fraud without reliance on manual feature engineering.
Designed the spatial-temporal attention-based neural network (STAN), integrating 3D convolution and attention mechanisms to jointly learn spatial and temporal transaction dynamics.
Evaluated detection performance against state-of-the-art baselines on a real-world fraud transaction dataset and conducted empirical post-analyses with domain experts.
STAN outperformed state-of-the-art baselines in both area under the ROC curve (AUC) and precision-recall curves.
Domain expert empirical evaluation confirmed the model's efficacy in flagging suspicious transactions and mining underlying fraud patterns.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Machine learning study demonstrates improved credit card fraud detection using spatio-temporal attention, indicating superior pattern recognition over traditional feature-engineering baselines.

Cite This Study

Cheng et al. (2020) studied this question.

synapsesocial.com/papers/6a0f4d1342feb5cfcf9bd001 https://doi.org/10.1609/aaai.v34i01.5371

View Full Paper

Ask AI

Bookmark

Implication

Machine learning study demonstrates improved credit card fraud detection using spatio-temporal attention, indicating superior pattern recognition over traditional feature-engineering baselines.

Spatio-Temporal Attention-Based Neural Network for Credit Card Fraud Detection

Key Points

Discussion

Implication

Cite This Study

Spatio-Temporal Attention-Based Neural Network for Credit Card Fraud Detection

Key Points

Discussion

Implication

Cite This Study

Keep reading

Keep reading