A weighted combination of GAN and VAE losses is reported to improve fraud detection F1 on the PaySim dataset, but the supporting experimental detail is missing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Application of Deep Generative Models for Anomaly Detection in Complex Financial Transactions
A weighted combination of GAN and VAE losses is reported to improve fraud detection F1 on the PaySim dataset, but the supporting experimental detail is missing.